/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Phi-3-mini-128k-instruct --quantization q4f32_1 --conv-template phi-3 --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC [2024-06-02 06:08:17] INFO auto_config.py:116: Found model configuration: /models/Phi-3-mini-128k-instruct/config.json [2024-06-02 06:08:17] INFO auto_config.py:154: Found model type: phi3. Use `--model-type` to override. [2024-06-02 06:08:17] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072) [2024-06-02 06:08:17] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048 [2024-06-02 06:08:17] INFO config.py:107: Overriding max_batch_size from 1 to 80 [2024-06-02 06:08:17] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 1 [2024-06-02 06:08:17] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [32000, 32001, 32007] [2024-06-02 06:08:17] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 32000 [2024-06-02 06:08:17] INFO gen_config.py:155: Found tokenizer config: /models/Phi-3-mini-128k-instruct/tokenizer.model. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer.model [2024-06-02 06:08:17] INFO gen_config.py:155: Found tokenizer config: /models/Phi-3-mini-128k-instruct/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer.json [2024-06-02 06:08:17] INFO gen_config.py:157: Not found tokenizer config: /models/Phi-3-mini-128k-instruct/vocab.json [2024-06-02 06:08:17] INFO gen_config.py:157: Not found tokenizer config: /models/Phi-3-mini-128k-instruct/merges.txt [2024-06-02 06:08:17] INFO gen_config.py:155: Found tokenizer config: /models/Phi-3-mini-128k-instruct/added_tokens.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/added_tokens.json [2024-06-02 06:08:17] INFO gen_config.py:155: Found tokenizer config: /models/Phi-3-mini-128k-instruct/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer_config.json [2024-06-02 06:08:17] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_fallback', 'prepend_space_in_encode': True, 'strip_space_in_decode': True} [2024-06-02 06:08:17] INFO gen_config.py:32: [System default] Setting temperature: 1.0 [2024-06-02 06:08:17] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0 [2024-06-02 06:08:17] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0 [2024-06-02 06:08:17] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0 [2024-06-02 06:08:17] INFO gen_config.py:32: [System default] Setting top_p: 1.0 [2024-06-02 06:08:17] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128 [2024-06-02 06:08:17] INFO gen_config.py:32: [System default] Setting max_gen_len: 512 [2024-06-02 06:08:17] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3 [2024-06-02 06:08:17] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/mlc-chat-config.json /opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Phi-3-mini-128k-instruct --quantization q4f32_1 --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC [2024-06-02 06:08:19] INFO auto_config.py:116: Found model configuration: /models/Phi-3-mini-128k-instruct/config.json [2024-06-02 06:08:20] INFO auto_device.py:79: Found device: cuda:0 [2024-06-02 06:08:21] INFO auto_device.py:88: Not found device: rocm:0 [2024-06-02 06:08:23] INFO auto_device.py:88: Not found device: metal:0 [2024-06-02 06:08:24] INFO auto_device.py:79: Found device: vulkan:0 [2024-06-02 06:08:24] INFO auto_device.py:79: Found device: vulkan:1 [2024-06-02 06:08:24] INFO auto_device.py:79: Found device: vulkan:2 [2024-06-02 06:08:24] INFO auto_device.py:79: Found device: vulkan:3 [2024-06-02 06:08:26] INFO auto_device.py:88: Not found device: opencl:0 [2024-06-02 06:08:26] INFO auto_device.py:35: Using device: cuda:0 [2024-06-02 06:08:26] INFO auto_weight.py:71: Finding weights in: /models/Phi-3-mini-128k-instruct [2024-06-02 06:08:26] INFO auto_weight.py:137: Not found Huggingface PyTorch [2024-06-02 06:08:26] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Phi-3-mini-128k-instruct/model.safetensors.index.json [2024-06-02 06:08:26] INFO auto_weight.py:107: Using source weight configuration: /models/Phi-3-mini-128k-instruct/model.safetensors.index.json. Use `--source` to override. [2024-06-02 06:08:26] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override. [2024-06-02 06:08:26] INFO auto_config.py:154: Found model type: phi3. Use `--model-type` to override. [2024-06-02 06:08:26] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072) [2024-06-02 06:08:26] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048 Weight conversion with arguments: --config /models/Phi-3-mini-128k-instruct/config.json --quantization GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7) --model-type phi3 --device cuda:0 --source /models/Phi-3-mini-128k-instruct/model.safetensors.index.json --source-format huggingface-safetensor --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC Start storing to cache /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC 0%| | 0/195 [00:00 type is zero. setattr(self, word, getattr(machar, word).flat[0]) /home/rickzhou/miniconda3/envs/mlc/lib/python3.11/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) 1%| | 1/195 [00:02<09:32, 2.95s/it] [2024-06-02 04:04:10] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.ln.weight", shape: (3072,), dtype: float32 1%| | 1/195 [00:02<09:32, 2.95s/it] [2024-06-02 04:04:10] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 8192), float32, cuda, axis=1, output_transpose=False) 1%| | 1/195 [00:02<09:32, 2.95s/it] [2024-06-02 04:04:11] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 1%| | 1/195 [00:03<09:32, 2.95s/it] [2024-06-02 04:04:11] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 1%| | 1/195 [00:03<09:32, 2.95s/it] 2%|▏ | 3/195 [00:03<02:50, 1.13it/s] [2024-06-02 04:04:11] INFO group_quantization.py:217: Compiling quantize function for key: ((16384, 3072), float32, cuda, axis=1, output_transpose=False) 2%|▏ | 3/195 [00:03<02:50, 1.13it/s] [2024-06-02 04:04:11] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 2%|▏ | 3/195 [00:03<02:50, 1.13it/s] [2024-06-02 04:04:11] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 2%|▏ | 3/195 [00:03<02:50, 1.13it/s] 2%|▏ | 4/195 [00:03<02:21, 1.35it/s] [2024-06-02 04:04:11] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.post_attention_layernorm.weight", shape: (3072,), dtype: float32 2%|▏ | 4/195 [00:03<02:21, 1.35it/s] [2024-06-02 04:04:11] INFO group_quantization.py:217: Compiling quantize function for key: ((9216, 3072), float32, cuda, axis=1, output_transpose=False) 2%|▏ | 4/195 [00:03<02:21, 1.35it/s] [2024-06-02 04:04:11] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 2%|▏ | 4/195 [00:04<02:21, 1.35it/s] [2024-06-02 04:04:11] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 2%|▏ | 4/195 [00:04<02:21, 1.35it/s] 3%|▎ | 6/195 [00:04<01:30, 2.09it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.ln.weight", shape: (3072,), dtype: float32 3%|▎ | 6/195 [00:04<01:30, 2.09it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 3%|▎ | 6/195 [00:04<01:30, 2.09it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 3%|▎ | 6/195 [00:04<01:30, 2.09it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 3%|▎ | 6/195 [00:04<01:30, 2.09it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 3%|▎ | 6/195 [00:04<01:30, 2.09it/s] 5%|▍ | 9/195 [00:04<00:49, 3.79it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.post_attention_layernorm.weight", shape: (3072,), dtype: float32 5%|▍ | 9/195 [00:04<00:49, 3.79it/s] [2024-06-02 04:04:12] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 3072), float32, cuda, axis=1, output_transpose=False) 5%|▍ | 9/195 [00:04<00:49, 3.79it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 5%|▍ | 9/195 [00:04<00:49, 3.79it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 5%|▍ | 9/195 [00:04<00:49, 3.79it/s] 6%|▌ | 11/195 [00:04<00:45, 4.03it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 6%|▌ | 11/195 [00:04<00:45, 4.03it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 6%|▌ | 11/195 [00:04<00:45, 4.03it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.ln.weight", shape: (3072,), dtype: float32 6%|▌ | 11/195 [00:04<00:45, 4.03it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 6%|▌ | 11/195 [00:04<00:45, 4.03it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 6%|▌ | 11/195 [00:04<00:45, 4.03it/s] 7%|▋ | 14/195 [00:04<00:29, 6.04it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 7%|▋ | 14/195 [00:04<00:29, 6.04it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 7%|▋ | 14/195 [00:05<00:29, 6.04it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.post_attention_layernorm.weight", shape: (3072,), dtype: float32 7%|▋ | 14/195 [00:05<00:29, 6.04it/s] 8%|▊ | 16/195 [00:05<00:25, 7.06it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 8%|▊ | 16/195 [00:05<00:25, 7.06it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 8%|▊ | 16/195 [00:05<00:25, 7.06it/s] [2024-06-02 04:04:12] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 8%|▊ | 16/195 [00:05<00:25, 7.06it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 8%|▊ | 16/195 [00:05<00:25, 7.06it/s] 9%|▉ | 18/195 [00:05<00:21, 8.31it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.ln.weight", shape: (3072,), dtype: float32 9%|▉ | 18/195 [00:05<00:21, 8.31it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 9%|▉ | 18/195 [00:05<00:21, 8.31it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 9%|▉ | 18/195 [00:05<00:21, 8.31it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 9%|▉ | 18/195 [00:05<00:21, 8.31it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 9%|▉ | 18/195 [00:05<00:21, 8.31it/s] 11%|█ | 21/195 [00:05<00:17, 10.19it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.post_attention_layernorm.weight", shape: (3072,), dtype: float32 11%|█ | 21/195 [00:05<00:17, 10.19it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 11%|█ | 21/195 [00:05<00:17, 10.19it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 11%|█ | 21/195 [00:05<00:17, 10.19it/s] 12%|█▏ | 23/195 [00:05<00:15, 10.94it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 12%|█▏ | 23/195 [00:05<00:15, 10.94it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 12%|█▏ | 23/195 [00:05<00:15, 10.94it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.ln.weight", shape: (3072,), dtype: float32 12%|█▏ | 23/195 [00:05<00:15, 10.94it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 12%|█▏ | 23/195 [00:05<00:15, 10.94it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 12%|█▏ | 23/195 [00:05<00:15, 10.94it/s] 13%|█▎ | 26/195 [00:05<00:12, 13.22it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 13%|█▎ | 26/195 [00:05<00:12, 13.22it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 13%|█▎ | 26/195 [00:05<00:12, 13.22it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.post_attention_layernorm.weight", shape: (3072,), dtype: float32 13%|█▎ | 26/195 [00:05<00:12, 13.22it/s] 14%|█▍ | 28/195 [00:05<00:12, 13.16it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 14%|█▍ | 28/195 [00:05<00:12, 13.16it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 14%|█▍ | 28/195 [00:05<00:12, 13.16it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 14%|█▍ | 28/195 [00:05<00:12, 13.16it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 14%|█▍ | 28/195 [00:05<00:12, 13.16it/s] 15%|█▌ | 30/195 [00:05<00:12, 13.74it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.ln.weight", shape: (3072,), dtype: float32 15%|█▌ | 30/195 [00:05<00:12, 13.74it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 15%|█▌ | 30/195 [00:06<00:12, 13.74it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 15%|█▌ | 30/195 [00:06<00:12, 13.74it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 15%|█▌ | 30/195 [00:06<00:12, 13.74it/s] [2024-06-02 04:04:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 15%|█▌ | 30/195 [00:06<00:12, 13.74it/s] 17%|█▋ | 33/195 [00:06<00:10, 14.76it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.post_attention_layernorm.weight", shape: (3072,), dtype: float32 17%|█▋ | 33/195 [00:06<00:10, 14.76it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 17%|█▋ | 33/195 [00:06<00:10, 14.76it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 17%|█▋ | 33/195 [00:06<00:10, 14.76it/s] 18%|█▊ | 35/195 [00:06<00:11, 14.38it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 18%|█▊ | 35/195 [00:06<00:11, 14.38it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 18%|█▊ | 35/195 [00:06<00:11, 14.38it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.ln.weight", shape: (3072,), dtype: float32 18%|█▊ | 35/195 [00:06<00:11, 14.38it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 18%|█▊ | 35/195 [00:06<00:11, 14.38it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 18%|█▊ | 35/195 [00:06<00:11, 14.38it/s] 19%|█▉ | 38/195 [00:06<00:09, 16.25it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 19%|█▉ | 38/195 [00:06<00:09, 16.25it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 19%|█▉ | 38/195 [00:06<00:09, 16.25it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.post_attention_layernorm.weight", shape: (3072,), dtype: float32 19%|█▉ | 38/195 [00:06<00:09, 16.25it/s] 21%|██ | 40/195 [00:06<00:10, 15.26it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 21%|██ | 40/195 [00:06<00:10, 15.26it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 21%|██ | 40/195 [00:06<00:10, 15.26it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 21%|██ | 40/195 [00:06<00:10, 15.26it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 21%|██ | 40/195 [00:06<00:10, 15.26it/s] 22%|██▏ | 42/195 [00:06<00:09, 15.38it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.ln.weight", shape: (3072,), dtype: float32 22%|██▏ | 42/195 [00:06<00:09, 15.38it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 22%|██▏ | 42/195 [00:06<00:09, 15.38it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 22%|██▏ | 42/195 [00:06<00:09, 15.38it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 22%|██▏ | 42/195 [00:06<00:09, 15.38it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 22%|██▏ | 42/195 [00:06<00:09, 15.38it/s] 23%|██▎ | 45/195 [00:06<00:09, 15.87it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.post_attention_layernorm.weight", shape: (3072,), dtype: float32 23%|██▎ | 45/195 [00:06<00:09, 15.87it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 23%|██▎ | 45/195 [00:06<00:09, 15.87it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 23%|██▎ | 45/195 [00:07<00:09, 15.87it/s] 24%|██▍ | 47/195 [00:07<00:09, 15.18it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 24%|██▍ | 47/195 [00:07<00:09, 15.18it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 24%|██▍ | 47/195 [00:07<00:09, 15.18it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.ln.weight", shape: (3072,), dtype: float32 24%|██▍ | 47/195 [00:07<00:09, 15.18it/s] [2024-06-02 04:04:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 24%|██▍ | 47/195 [00:07<00:09, 15.18it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 24%|██▍ | 47/195 [00:07<00:09, 15.18it/s] 26%|██▌ | 50/195 [00:07<00:08, 16.86it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 26%|██▌ | 50/195 [00:07<00:08, 16.86it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 26%|██▌ | 50/195 [00:07<00:08, 16.86it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.post_attention_layernorm.weight", shape: (3072,), dtype: float32 26%|██▌ | 50/195 [00:07<00:08, 16.86it/s] 27%|██▋ | 52/195 [00:07<00:09, 15.70it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 27%|██▋ | 52/195 [00:07<00:09, 15.70it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 27%|██▋ | 52/195 [00:07<00:09, 15.70it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 27%|██▋ | 52/195 [00:07<00:09, 15.70it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 27%|██▋ | 52/195 [00:07<00:09, 15.70it/s] 28%|██▊ | 54/195 [00:07<00:08, 15.74it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.ln.weight", shape: (3072,), dtype: float32 28%|██▊ | 54/195 [00:07<00:08, 15.74it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 28%|██▊ | 54/195 [00:07<00:08, 15.74it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 28%|██▊ | 54/195 [00:07<00:08, 15.74it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 28%|██▊ | 54/195 [00:07<00:08, 15.74it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 28%|██▊ | 54/195 [00:07<00:08, 15.74it/s] 29%|██▉ | 57/195 [00:07<00:08, 16.13it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.post_attention_layernorm.weight", shape: (3072,), dtype: float32 29%|██▉ | 57/195 [00:07<00:08, 16.13it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 29%|██▉ | 57/195 [00:07<00:08, 16.13it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 29%|██▉ | 57/195 [00:07<00:08, 16.13it/s] 30%|███ | 59/195 [00:07<00:08, 15.46it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 30%|███ | 59/195 [00:07<00:08, 15.46it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 30%|███ | 59/195 [00:07<00:08, 15.46it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.ln.weight", shape: (3072,), dtype: float32 30%|███ | 59/195 [00:07<00:08, 15.46it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 30%|███ | 59/195 [00:07<00:08, 15.46it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 30%|███ | 59/195 [00:07<00:08, 15.46it/s] 32%|███▏ | 62/195 [00:07<00:07, 17.07it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 32%|███▏ | 62/195 [00:07<00:07, 17.07it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 32%|███▏ | 62/195 [00:08<00:07, 17.07it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.post_attention_layernorm.weight", shape: (3072,), dtype: float32 32%|███▏ | 62/195 [00:08<00:07, 17.07it/s] 33%|███▎ | 64/195 [00:08<00:08, 15.74it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 33%|███▎ | 64/195 [00:08<00:08, 15.74it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 33%|███▎ | 64/195 [00:08<00:08, 15.74it/s] [2024-06-02 04:04:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 33%|███▎ | 64/195 [00:08<00:08, 15.74it/s] [2024-06-02 04:04:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 33%|███▎ | 64/195 [00:08<00:08, 15.74it/s] 34%|███▍ | 66/195 [00:08<00:08, 15.69it/s] [2024-06-02 04:04:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.norm.weight", shape: (3072,), dtype: float32 34%|███▍ | 66/195 [00:08<00:08, 15.69it/s] [2024-06-02 04:04:16] INFO huggingface_loader.py:196: Unloading HF weight file: /ssd1/rickzhou/models/Phi-3-mini-128k-instruct/model-00002-of-00002.safetensors 34%|███▍ | 66/195 [00:08<00:08, 15.69it/s] [2024-06-02 04:04:16] INFO huggingface_loader.py:184: Loading HF parameters from: /ssd1/rickzhou/models/Phi-3-mini-128k-instruct/model-00001-of-00002.safetensors 34%|███▍ | 66/195 [00:08<00:08, 15.69it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.embd.q_weight", shape: (32064, 384), dtype: uint32 34%|███▍ | 66/195 [00:09<00:08, 15.69it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.embd.q_scale", shape: (32064, 96), dtype: float32 34%|███▍ | 66/195 [00:09<00:08, 15.69it/s] 35%|███▍ | 68/195 [00:09<00:26, 4.71it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.ln.weight", shape: (3072,), dtype: float32 35%|███▍ | 68/195 [00:09<00:26, 4.71it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 35%|███▍ | 68/195 [00:09<00:26, 4.71it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 35%|███▍ | 68/195 [00:09<00:26, 4.71it/s] 36%|███▌ | 70/195 [00:09<00:21, 5.87it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 36%|███▌ | 70/195 [00:09<00:21, 5.87it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 36%|███▌ | 70/195 [00:09<00:21, 5.87it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.post_attention_layernorm.weight", shape: (3072,), dtype: float32 36%|███▌ | 70/195 [00:09<00:21, 5.87it/s] 37%|███▋ | 72/195 [00:09<00:17, 6.96it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 37%|███▋ | 72/195 [00:09<00:17, 6.96it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 37%|███▋ | 72/195 [00:09<00:17, 6.96it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 37%|███▋ | 72/195 [00:09<00:17, 6.96it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 37%|███▋ | 72/195 [00:09<00:17, 6.96it/s] 38%|███▊ | 74/195 [00:09<00:14, 8.21it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.ln.weight", shape: (3072,), dtype: float32 38%|███▊ | 74/195 [00:09<00:14, 8.21it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 38%|███▊ | 74/195 [00:09<00:14, 8.21it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 38%|███▊ | 74/195 [00:09<00:14, 8.21it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 38%|███▊ | 74/195 [00:09<00:14, 8.21it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 38%|███▊ | 74/195 [00:10<00:14, 8.21it/s] 39%|███▉ | 77/195 [00:10<00:11, 10.20it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.post_attention_layernorm.weight", shape: (3072,), dtype: float32 39%|███▉ | 77/195 [00:10<00:11, 10.20it/s] [2024-06-02 04:04:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 39%|███▉ | 77/195 [00:10<00:11, 10.20it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 39%|███▉ | 77/195 [00:10<00:11, 10.20it/s] 41%|████ | 79/195 [00:10<00:10, 11.01it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 41%|████ | 79/195 [00:10<00:10, 11.01it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 41%|████ | 79/195 [00:10<00:10, 11.01it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.ln.weight", shape: (3072,), dtype: float32 41%|████ | 79/195 [00:10<00:10, 11.01it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 41%|████ | 79/195 [00:10<00:10, 11.01it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 41%|████ | 79/195 [00:10<00:10, 11.01it/s] 42%|████▏ | 82/195 [00:10<00:08, 13.24it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 42%|████▏ | 82/195 [00:10<00:08, 13.24it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 42%|████▏ | 82/195 [00:10<00:08, 13.24it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.post_attention_layernorm.weight", shape: (3072,), dtype: float32 42%|████▏ | 82/195 [00:10<00:08, 13.24it/s] 43%|████▎ | 84/195 [00:10<00:08, 13.21it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 43%|████▎ | 84/195 [00:10<00:08, 13.21it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 43%|████▎ | 84/195 [00:10<00:08, 13.21it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 43%|████▎ | 84/195 [00:10<00:08, 13.21it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 43%|████▎ | 84/195 [00:10<00:08, 13.21it/s] 44%|████▍ | 86/195 [00:10<00:07, 13.76it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.ln.weight", shape: (3072,), dtype: float32 44%|████▍ | 86/195 [00:10<00:07, 13.76it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 44%|████▍ | 86/195 [00:10<00:07, 13.76it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 44%|████▍ | 86/195 [00:10<00:07, 13.76it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 44%|████▍ | 86/195 [00:10<00:07, 13.76it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 44%|████▍ | 86/195 [00:10<00:07, 13.76it/s] 46%|████▌ | 89/195 [00:10<00:07, 14.74it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.post_attention_layernorm.weight", shape: (3072,), dtype: float32 46%|████▌ | 89/195 [00:10<00:07, 14.74it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 46%|████▌ | 89/195 [00:10<00:07, 14.74it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 46%|████▌ | 89/195 [00:10<00:07, 14.74it/s] 47%|████▋ | 91/195 [00:10<00:07, 14.37it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 47%|████▋ | 91/195 [00:10<00:07, 14.37it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 47%|████▋ | 91/195 [00:10<00:07, 14.37it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.ln.weight", shape: (3072,), dtype: float32 47%|████▋ | 91/195 [00:10<00:07, 14.37it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 47%|████▋ | 91/195 [00:10<00:07, 14.37it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 47%|████▋ | 91/195 [00:11<00:07, 14.37it/s] 48%|████▊ | 94/195 [00:11<00:06, 16.05it/s] [2024-06-02 04:04:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 48%|████▊ | 94/195 [00:11<00:06, 16.05it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 48%|████▊ | 94/195 [00:11<00:06, 16.05it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.post_attention_layernorm.weight", shape: (3072,), dtype: float32 48%|████▊ | 94/195 [00:11<00:06, 16.05it/s] 49%|████▉ | 96/195 [00:11<00:06, 15.19it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 49%|████▉ | 96/195 [00:11<00:06, 15.19it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 49%|████▉ | 96/195 [00:11<00:06, 15.19it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 49%|████▉ | 96/195 [00:11<00:06, 15.19it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 49%|████▉ | 96/195 [00:11<00:06, 15.19it/s] 50%|█████ | 98/195 [00:11<00:06, 15.20it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.ln.weight", shape: (3072,), dtype: float32 50%|█████ | 98/195 [00:11<00:06, 15.20it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 50%|█████ | 98/195 [00:11<00:06, 15.20it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 50%|█████ | 98/195 [00:11<00:06, 15.20it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 50%|█████ | 98/195 [00:11<00:06, 15.20it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 50%|█████ | 98/195 [00:11<00:06, 15.20it/s] 52%|█████▏ | 101/195 [00:11<00:05, 15.70it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.post_attention_layernorm.weight", shape: (3072,), dtype: float32 52%|█████▏ | 101/195 [00:11<00:05, 15.70it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 52%|█████▏ | 101/195 [00:11<00:05, 15.70it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 52%|█████▏ | 101/195 [00:11<00:05, 15.70it/s] 53%|█████▎ | 103/195 [00:11<00:06, 15.03it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 53%|█████▎ | 103/195 [00:11<00:06, 15.03it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 53%|█████▎ | 103/195 [00:11<00:06, 15.03it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.ln.weight", shape: (3072,), dtype: float32 53%|█████▎ | 103/195 [00:11<00:06, 15.03it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 53%|█████▎ | 103/195 [00:11<00:06, 15.03it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 53%|█████▎ | 103/195 [00:11<00:06, 15.03it/s] 54%|█████▍ | 106/195 [00:11<00:05, 16.62it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 54%|█████▍ | 106/195 [00:11<00:05, 16.62it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 54%|█████▍ | 106/195 [00:11<00:05, 16.62it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.post_attention_layernorm.weight", shape: (3072,), dtype: float32 54%|█████▍ | 106/195 [00:12<00:05, 16.62it/s] 55%|█████▌ | 108/195 [00:12<00:05, 15.57it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 55%|█████▌ | 108/195 [00:12<00:05, 15.57it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 55%|█████▌ | 108/195 [00:12<00:05, 15.57it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 55%|█████▌ | 108/195 [00:12<00:05, 15.57it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 55%|█████▌ | 108/195 [00:12<00:05, 15.57it/s] 56%|█████▋ | 110/195 [00:12<00:05, 15.52it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.ln.weight", shape: (3072,), dtype: float32 56%|█████▋ | 110/195 [00:12<00:05, 15.52it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 56%|█████▋ | 110/195 [00:12<00:05, 15.52it/s] [2024-06-02 04:04:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 56%|█████▋ | 110/195 [00:12<00:05, 15.52it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 56%|█████▋ | 110/195 [00:12<00:05, 15.52it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 56%|█████▋ | 110/195 [00:12<00:05, 15.52it/s] 58%|█████▊ | 113/195 [00:12<00:05, 15.95it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.post_attention_layernorm.weight", shape: (3072,), dtype: float32 58%|█████▊ | 113/195 [00:12<00:05, 15.95it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 58%|█████▊ | 113/195 [00:12<00:05, 15.95it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 58%|█████▊ | 113/195 [00:12<00:05, 15.95it/s] 59%|█████▉ | 115/195 [00:12<00:05, 15.22it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 59%|█████▉ | 115/195 [00:12<00:05, 15.22it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 59%|█████▉ | 115/195 [00:12<00:05, 15.22it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.ln.weight", shape: (3072,), dtype: float32 59%|█████▉ | 115/195 [00:12<00:05, 15.22it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 59%|█████▉ | 115/195 [00:12<00:05, 15.22it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 59%|█████▉ | 115/195 [00:12<00:05, 15.22it/s] 61%|██████ | 118/195 [00:12<00:04, 16.78it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 61%|██████ | 118/195 [00:12<00:04, 16.78it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 61%|██████ | 118/195 [00:12<00:04, 16.78it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.post_attention_layernorm.weight", shape: (3072,), dtype: float32 61%|██████ | 118/195 [00:12<00:04, 16.78it/s] 62%|██████▏ | 120/195 [00:12<00:04, 15.44it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 62%|██████▏ | 120/195 [00:12<00:04, 15.44it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 62%|██████▏ | 120/195 [00:12<00:04, 15.44it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 62%|██████▏ | 120/195 [00:12<00:04, 15.44it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 62%|██████▏ | 120/195 [00:12<00:04, 15.44it/s] 63%|██████▎ | 122/195 [00:12<00:04, 15.41it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.ln.weight", shape: (3072,), dtype: float32 63%|██████▎ | 122/195 [00:12<00:04, 15.41it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 63%|██████▎ | 122/195 [00:12<00:04, 15.41it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 63%|██████▎ | 122/195 [00:12<00:04, 15.41it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 63%|██████▎ | 122/195 [00:12<00:04, 15.41it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 63%|██████▎ | 122/195 [00:13<00:04, 15.41it/s] 64%|██████▍ | 125/195 [00:13<00:04, 15.86it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.post_attention_layernorm.weight", shape: (3072,), dtype: float32 64%|██████▍ | 125/195 [00:13<00:04, 15.86it/s] [2024-06-02 04:04:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 64%|██████▍ | 125/195 [00:13<00:04, 15.86it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 64%|██████▍ | 125/195 [00:13<00:04, 15.86it/s] 65%|██████▌ | 127/195 [00:13<00:04, 15.06it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 65%|██████▌ | 127/195 [00:13<00:04, 15.06it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 65%|██████▌ | 127/195 [00:13<00:04, 15.06it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.ln.weight", shape: (3072,), dtype: float32 65%|██████▌ | 127/195 [00:13<00:04, 15.06it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 65%|██████▌ | 127/195 [00:13<00:04, 15.06it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 65%|██████▌ | 127/195 [00:13<00:04, 15.06it/s] 67%|██████▋ | 130/195 [00:13<00:03, 16.51it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 67%|██████▋ | 130/195 [00:13<00:03, 16.51it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 67%|██████▋ | 130/195 [00:13<00:03, 16.51it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.post_attention_layernorm.weight", shape: (3072,), dtype: float32 67%|██████▋ | 130/195 [00:13<00:03, 16.51it/s] 68%|██████▊ | 132/195 [00:13<00:04, 15.40it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 68%|██████▊ | 132/195 [00:13<00:04, 15.40it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 68%|██████▊ | 132/195 [00:13<00:04, 15.40it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 68%|██████▊ | 132/195 [00:13<00:04, 15.40it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 68%|██████▊ | 132/195 [00:13<00:04, 15.40it/s] 69%|██████▊ | 134/195 [00:13<00:03, 15.38it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.ln.weight", shape: (3072,), dtype: float32 69%|██████▊ | 134/195 [00:13<00:03, 15.38it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 69%|██████▊ | 134/195 [00:13<00:03, 15.38it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 69%|██████▊ | 134/195 [00:13<00:03, 15.38it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 69%|██████▊ | 134/195 [00:13<00:03, 15.38it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 69%|██████▊ | 134/195 [00:13<00:03, 15.38it/s] 70%|███████ | 137/195 [00:13<00:03, 15.88it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.post_attention_layernorm.weight", shape: (3072,), dtype: float32 70%|███████ | 137/195 [00:13<00:03, 15.88it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 70%|███████ | 137/195 [00:13<00:03, 15.88it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 70%|███████ | 137/195 [00:13<00:03, 15.88it/s] 71%|███████▏ | 139/195 [00:13<00:03, 15.14it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 71%|███████▏ | 139/195 [00:14<00:03, 15.14it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 71%|███████▏ | 139/195 [00:14<00:03, 15.14it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.ln.weight", shape: (3072,), dtype: float32 71%|███████▏ | 139/195 [00:14<00:03, 15.14it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 71%|███████▏ | 139/195 [00:14<00:03, 15.14it/s] [2024-06-02 04:04:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 71%|███████▏ | 139/195 [00:14<00:03, 15.14it/s] 73%|███████▎ | 142/195 [00:14<00:03, 16.71it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 73%|███████▎ | 142/195 [00:14<00:03, 16.71it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 73%|███████▎ | 142/195 [00:14<00:03, 16.71it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.post_attention_layernorm.weight", shape: (3072,), dtype: float32 73%|███████▎ | 142/195 [00:14<00:03, 16.71it/s] 74%|███████▍ | 144/195 [00:14<00:03, 15.59it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 74%|███████▍ | 144/195 [00:14<00:03, 15.59it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 74%|███████▍ | 144/195 [00:14<00:03, 15.59it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 74%|███████▍ | 144/195 [00:14<00:03, 15.59it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 74%|███████▍ | 144/195 [00:14<00:03, 15.59it/s] 75%|███████▍ | 146/195 [00:14<00:03, 15.45it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.ln.weight", shape: (3072,), dtype: float32 75%|███████▍ | 146/195 [00:14<00:03, 15.45it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 75%|███████▍ | 146/195 [00:14<00:03, 15.45it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 75%|███████▍ | 146/195 [00:14<00:03, 15.45it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 75%|███████▍ | 146/195 [00:14<00:03, 15.45it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 75%|███████▍ | 146/195 [00:14<00:03, 15.45it/s] 76%|███████▋ | 149/195 [00:14<00:02, 15.91it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.post_attention_layernorm.weight", shape: (3072,), dtype: float32 76%|███████▋ | 149/195 [00:14<00:02, 15.91it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 76%|███████▋ | 149/195 [00:14<00:02, 15.91it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 76%|███████▋ | 149/195 [00:14<00:02, 15.91it/s] 77%|███████▋ | 151/195 [00:14<00:02, 15.15it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 77%|███████▋ | 151/195 [00:14<00:02, 15.15it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 77%|███████▋ | 151/195 [00:14<00:02, 15.15it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 77%|███████▋ | 151/195 [00:14<00:02, 15.15it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 77%|███████▋ | 151/195 [00:14<00:02, 15.15it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.ln.weight", shape: (3072,), dtype: float32 77%|███████▋ | 151/195 [00:14<00:02, 15.15it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 77%|███████▋ | 151/195 [00:14<00:02, 15.15it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 77%|███████▋ | 151/195 [00:14<00:02, 15.15it/s] 79%|███████▉ | 155/195 [00:14<00:02, 17.25it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 79%|███████▉ | 155/195 [00:14<00:02, 17.25it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 79%|███████▉ | 155/195 [00:15<00:02, 17.25it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.post_attention_layernorm.weight", shape: (3072,), dtype: float32 79%|███████▉ | 155/195 [00:15<00:02, 17.25it/s] 81%|████████ | 157/195 [00:15<00:02, 16.07it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 81%|████████ | 157/195 [00:15<00:02, 16.07it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 81%|████████ | 157/195 [00:15<00:02, 16.07it/s] [2024-06-02 04:04:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 81%|████████ | 157/195 [00:15<00:02, 16.07it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 81%|████████ | 157/195 [00:15<00:02, 16.07it/s] 82%|████████▏ | 159/195 [00:15<00:02, 15.90it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.ln.weight", shape: (3072,), dtype: float32 82%|████████▏ | 159/195 [00:15<00:02, 15.90it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 82%|████████▏ | 159/195 [00:15<00:02, 15.90it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 82%|████████▏ | 159/195 [00:15<00:02, 15.90it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 82%|████████▏ | 159/195 [00:15<00:02, 15.90it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 82%|████████▏ | 159/195 [00:15<00:02, 15.90it/s] 83%|████████▎ | 162/195 [00:15<00:02, 15.89it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.post_attention_layernorm.weight", shape: (3072,), dtype: float32 83%|████████▎ | 162/195 [00:15<00:02, 15.89it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 83%|████████▎ | 162/195 [00:15<00:02, 15.89it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 83%|████████▎ | 162/195 [00:15<00:02, 15.89it/s] 84%|████████▍ | 164/195 [00:15<00:02, 15.16it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 84%|████████▍ | 164/195 [00:15<00:02, 15.16it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 84%|████████▍ | 164/195 [00:15<00:02, 15.16it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.ln.weight", shape: (3072,), dtype: float32 84%|████████▍ | 164/195 [00:15<00:02, 15.16it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 84%|████████▍ | 164/195 [00:15<00:02, 15.16it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 84%|████████▍ | 164/195 [00:15<00:02, 15.16it/s] 86%|████████▌ | 167/195 [00:15<00:01, 16.65it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 86%|████████▌ | 167/195 [00:15<00:01, 16.65it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 86%|████████▌ | 167/195 [00:15<00:01, 16.65it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.post_attention_layernorm.weight", shape: (3072,), dtype: float32 86%|████████▌ | 167/195 [00:15<00:01, 16.65it/s] 87%|████████▋ | 169/195 [00:15<00:01, 15.58it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 87%|████████▋ | 169/195 [00:15<00:01, 15.58it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 87%|████████▋ | 169/195 [00:15<00:01, 15.58it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 87%|████████▋ | 169/195 [00:15<00:01, 15.58it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 87%|████████▋ | 169/195 [00:15<00:01, 15.58it/s] 88%|████████▊ | 171/195 [00:15<00:01, 15.46it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.ln.weight", shape: (3072,), dtype: float32 88%|████████▊ | 171/195 [00:15<00:01, 15.46it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 88%|████████▊ | 171/195 [00:16<00:01, 15.46it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 88%|████████▊ | 171/195 [00:16<00:01, 15.46it/s] [2024-06-02 04:04:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 88%|████████▊ | 171/195 [00:16<00:01, 15.46it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 88%|████████▊ | 171/195 [00:16<00:01, 15.46it/s] 89%|████████▉ | 174/195 [00:16<00:01, 15.88it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.post_attention_layernorm.weight", shape: (3072,), dtype: float32 89%|████████▉ | 174/195 [00:16<00:01, 15.88it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 89%|████████▉ | 174/195 [00:16<00:01, 15.88it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 89%|████████▉ | 174/195 [00:16<00:01, 15.88it/s] 90%|█████████ | 176/195 [00:16<00:01, 15.16it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 90%|█████████ | 176/195 [00:16<00:01, 15.16it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 90%|█████████ | 176/195 [00:16<00:01, 15.16it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.ln.weight", shape: (3072,), dtype: float32 90%|█████████ | 176/195 [00:16<00:01, 15.16it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 90%|█████████ | 176/195 [00:16<00:01, 15.16it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 90%|█████████ | 176/195 [00:16<00:01, 15.16it/s] 92%|█████████▏| 179/195 [00:16<00:00, 16.70it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 92%|█████████▏| 179/195 [00:16<00:00, 16.70it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 92%|█████████▏| 179/195 [00:16<00:00, 16.70it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.post_attention_layernorm.weight", shape: (3072,), dtype: float32 92%|█████████▏| 179/195 [00:16<00:00, 16.70it/s] 93%|█████████▎| 181/195 [00:16<00:00, 15.63it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 93%|█████████▎| 181/195 [00:16<00:00, 15.63it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 93%|█████████▎| 181/195 [00:16<00:00, 15.63it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 93%|█████████▎| 181/195 [00:16<00:00, 15.63it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 93%|█████████▎| 181/195 [00:16<00:00, 15.63it/s] 94%|█████████▍| 183/195 [00:16<00:00, 15.48it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.ln.weight", shape: (3072,), dtype: float32 94%|█████████▍| 183/195 [00:16<00:00, 15.48it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 94%|█████████▍| 183/195 [00:16<00:00, 15.48it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 94%|█████████▍| 183/195 [00:16<00:00, 15.48it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 94%|█████████▍| 183/195 [00:16<00:00, 15.48it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 94%|█████████▍| 183/195 [00:16<00:00, 15.48it/s] 95%|█████████▌| 186/195 [00:16<00:00, 15.91it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.post_attention_layernorm.weight", shape: (3072,), dtype: float32 95%|█████████▌| 186/195 [00:16<00:00, 15.91it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 95%|█████████▌| 186/195 [00:16<00:00, 15.91it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 95%|█████████▌| 186/195 [00:17<00:00, 15.91it/s] 96%|█████████▋| 188/195 [00:17<00:00, 15.15it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 96%|█████████▋| 188/195 [00:17<00:00, 15.15it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 96%|█████████▋| 188/195 [00:17<00:00, 15.15it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.ln.weight", shape: (3072,), dtype: float32 96%|█████████▋| 188/195 [00:17<00:00, 15.15it/s] [2024-06-02 04:04:24] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 96%|█████████▋| 188/195 [00:17<00:00, 15.15it/s] [2024-06-02 04:04:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 96%|█████████▋| 188/195 [00:17<00:00, 15.15it/s] 98%|█████████▊| 191/195 [00:17<00:00, 16.72it/s] [2024-06-02 04:04:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 98%|█████████▊| 191/195 [00:17<00:00, 16.72it/s] [2024-06-02 04:04:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 98%|█████████▊| 191/195 [00:17<00:00, 16.72it/s] [2024-06-02 04:04:25] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.post_attention_layernorm.weight", shape: (3072,), dtype: float32 98%|█████████▊| 191/195 [00:17<00:00, 16.72it/s] 99%|█████████▉| 193/195 [00:17<00:00, 15.62it/s] [2024-06-02 04:04:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 99%|█████████▉| 193/195 [00:17<00:00, 15.62it/s] [2024-06-02 04:04:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 99%|█████████▉| 193/195 [00:17<00:00, 15.62it/s] [2024-06-02 04:04:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 99%|█████████▉| 193/195 [00:17<00:00, 15.62it/s] [2024-06-02 04:04:25] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 99%|█████████▉| 193/195 [00:17<00:00, 15.62it/s] 100%|██████████| 195/195 [00:17<00:00, 15.48it/s] 100%|██████████| 195/195 [00:17<00:00, 11.13it/s] [2024-06-02 04:04:25] INFO huggingface_loader.py:196: Unloading HF weight file: /ssd1/rickzhou/models/Phi-3-mini-128k-instruct/model-00001-of-00002.safetensors [2024-06-02 04:04:25] INFO stats.py:76: Time usage: HF loading: 2.646 sec; Pre-quantization mapping: 1.733 sec; Quantization: 2.463 sec [2024-06-02 04:04:25] INFO stats.py:90: RAM usage: Peak RAM: 9.262 GB. Total bytes loaded from disk: 14.235 GB [2024-06-02 04:04:25] INFO convert_weight.py:155: Parameter size after quantization: 2.225 GB [2024-06-02 04:04:25] INFO convert_weight.py:160: Total parameters: 3,821,079,552 [2024-06-02 04:04:25] INFO convert_weight.py:161: Bits per parameter: 5.001 [2024-06-02 04:04:25] INFO convert_weight.py:166: Saved to directory: /ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC All finished, 83 total shards committed, record saved to /ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/ndarray-cache.json Also saved a bf16 record to /ssd2/models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/ndarray-cache-b16.json /opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/Phi-3-mini-128k-instruct --quantization q4f32_1 --conv-template phi-3 --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC [2024-06-04 02:47:01] INFO auto_config.py:116: Found model configuration: /models/Phi-3-mini-128k-instruct/config.json [2024-06-04 02:47:01] INFO auto_config.py:154: Found model type: phi3. Use `--model-type` to override. [2024-06-04 02:47:01] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072) [2024-06-04 02:47:01] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048 [2024-06-04 02:47:01] INFO config.py:107: Overriding max_batch_size from 1 to 80 [2024-06-04 02:47:01] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 1 [2024-06-04 02:47:01] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [32000, 32001, 32007] [2024-06-04 02:47:01] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 32000 [2024-06-04 02:47:01] INFO gen_config.py:155: Found tokenizer config: /models/Phi-3-mini-128k-instruct/tokenizer.model. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer.model [2024-06-04 02:47:01] INFO gen_config.py:155: Found tokenizer config: /models/Phi-3-mini-128k-instruct/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer.json [2024-06-04 02:47:01] INFO gen_config.py:157: Not found tokenizer config: /models/Phi-3-mini-128k-instruct/vocab.json [2024-06-04 02:47:01] INFO gen_config.py:157: Not found tokenizer config: /models/Phi-3-mini-128k-instruct/merges.txt [2024-06-04 02:47:01] INFO gen_config.py:155: Found tokenizer config: /models/Phi-3-mini-128k-instruct/added_tokens.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/added_tokens.json [2024-06-04 02:47:01] INFO gen_config.py:155: Found tokenizer config: /models/Phi-3-mini-128k-instruct/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer_config.json [2024-06-04 02:47:01] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_fallback', 'prepend_space_in_encode': True, 'strip_space_in_decode': True} [2024-06-04 02:47:01] INFO gen_config.py:32: [System default] Setting temperature: 1.0 [2024-06-04 02:47:01] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0 [2024-06-04 02:47:01] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0 [2024-06-04 02:47:01] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0 [2024-06-04 02:47:01] INFO gen_config.py:32: [System default] Setting top_p: 1.0 [2024-06-04 02:47:01] INFO gen_config.py:32: [System default] Setting mean_gen_len: 128 [2024-06-04 02:47:01] INFO gen_config.py:32: [System default] Setting max_gen_len: 512 [2024-06-04 02:47:01] INFO gen_config.py:32: [System default] Setting shift_fill_factor: 0.3 [2024-06-04 02:47:01] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/mlc-chat-config.json /opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/Phi-3-mini-128k-instruct --quantization q4f32_1 --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC [2024-06-04 02:47:02] INFO auto_config.py:116: Found model configuration: /models/Phi-3-mini-128k-instruct/config.json [2024-06-04 02:47:04] INFO auto_device.py:79: Found device: cuda:0 [2024-06-04 02:47:05] INFO auto_device.py:88: Not found device: rocm:0 [2024-06-04 02:47:07] INFO auto_device.py:88: Not found device: metal:0 [2024-06-04 02:47:09] INFO auto_device.py:79: Found device: vulkan:0 [2024-06-04 02:47:09] INFO auto_device.py:79: Found device: vulkan:1 [2024-06-04 02:47:09] INFO auto_device.py:79: Found device: vulkan:2 [2024-06-04 02:47:09] INFO auto_device.py:79: Found device: vulkan:3 [2024-06-04 02:47:10] INFO auto_device.py:88: Not found device: opencl:0 [2024-06-04 02:47:10] INFO auto_device.py:35: Using device: cuda:0 [2024-06-04 02:47:10] INFO auto_weight.py:71: Finding weights in: /models/Phi-3-mini-128k-instruct [2024-06-04 02:47:10] INFO auto_weight.py:137: Not found Huggingface PyTorch [2024-06-04 02:47:10] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /models/Phi-3-mini-128k-instruct/model.safetensors.index.json [2024-06-04 02:47:10] INFO auto_weight.py:107: Using source weight configuration: /models/Phi-3-mini-128k-instruct/model.safetensors.index.json. Use `--source` to override. [2024-06-04 02:47:10] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override. [2024-06-04 02:47:10] INFO auto_config.py:154: Found model type: phi3. Use `--model-type` to override. [2024-06-04 02:47:10] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072) [2024-06-04 02:47:10] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048 Weight conversion with arguments: --config /models/Phi-3-mini-128k-instruct/config.json --quantization GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7) --model-type phi3 --device cuda:0 --source /models/Phi-3-mini-128k-instruct/model.safetensors.index.json --source-format huggingface-safetensor --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC Start storing to cache /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC 0%| | 0/195 [00:00 type is zero. setattr(self, word, getattr(machar, word).flat[0]) /home/rickzhou/miniconda3/envs/mlc/lib/python3.11/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) 1%| | 1/195 [00:08<28:01, 8.67s/it] [2024-06-11 04:34:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.21.ln.weight", shape: (3072,), dtype: float32 1%| | 1/195 [00:08<28:01, 8.67s/it] [2024-06-11 04:34:34] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 8192), float32, cuda, axis=1, output_transpose=False) 1%| | 1/195 [00:08<28:01, 8.67s/it] [2024-06-11 04:34:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 1%| | 1/195 [00:08<28:01, 8.67s/it] [2024-06-11 04:34:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 1%| | 1/195 [00:08<28:01, 8.67s/it] 2%|▏ | 3/195 [00:08<07:34, 2.37s/it] [2024-06-11 04:34:35] INFO group_quantization.py:217: Compiling quantize function for key: ((16384, 3072), float32, cuda, axis=1, output_transpose=False) 2%|▏ | 3/195 [00:09<07:34, 2.37s/it] [2024-06-11 04:34:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 2%|▏ | 3/195 [00:09<07:34, 2.37s/it] [2024-06-11 04:34:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 2%|▏ | 3/195 [00:09<07:34, 2.37s/it] 2%|▏ | 4/195 [00:09<05:24, 1.70s/it] [2024-06-11 04:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.21.post_attention_layernorm.weight", shape: (3072,), dtype: float32 2%|▏ | 4/195 [00:09<05:24, 1.70s/it] [2024-06-11 04:34:35] INFO group_quantization.py:217: Compiling quantize function for key: ((9216, 3072), float32, cuda, axis=1, output_transpose=False) 2%|▏ | 4/195 [00:09<05:24, 1.70s/it] [2024-06-11 04:34:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 2%|▏ | 4/195 [00:09<05:24, 1.70s/it] [2024-06-11 04:34:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 2%|▏ | 4/195 [00:09<05:24, 1.70s/it] 3%|▎ | 6/195 [00:09<03:01, 1.04it/s] [2024-06-11 04:34:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.22.ln.weight", shape: (3072,), dtype: float32 3%|▎ | 6/195 [00:09<03:01, 1.04it/s] [2024-06-11 04:34:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 3%|▎ | 6/195 [00:09<03:01, 1.04it/s] [2024-06-11 04:34:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 3%|▎ | 6/195 [00:09<03:01, 1.04it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 3%|▎ | 6/195 [00:09<03:01, 1.04it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 3%|▎ | 6/195 [00:10<03:01, 1.04it/s] 5%|▍ | 9/195 [00:10<01:32, 2.02it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.22.post_attention_layernorm.weight", shape: (3072,), dtype: float32 5%|▍ | 9/195 [00:10<01:32, 2.02it/s] [2024-06-11 04:34:36] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 3072), float32, cuda, axis=1, output_transpose=False) 5%|▍ | 9/195 [00:10<01:32, 2.02it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 5%|▍ | 9/195 [00:10<01:32, 2.02it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 5%|▍ | 9/195 [00:10<01:32, 2.02it/s] 6%|▌ | 11/195 [00:10<01:14, 2.47it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 6%|▌ | 11/195 [00:10<01:14, 2.47it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 6%|▌ | 11/195 [00:10<01:14, 2.47it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.23.ln.weight", shape: (3072,), dtype: float32 6%|▌ | 11/195 [00:10<01:14, 2.47it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 6%|▌ | 11/195 [00:10<01:14, 2.47it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 6%|▌ | 11/195 [00:10<01:14, 2.47it/s] 7%|▋ | 14/195 [00:10<00:46, 3.93it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 7%|▋ | 14/195 [00:10<00:46, 3.93it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 7%|▋ | 14/195 [00:10<00:46, 3.93it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.23.post_attention_layernorm.weight", shape: (3072,), dtype: float32 7%|▋ | 14/195 [00:10<00:46, 3.93it/s] 8%|▊ | 16/195 [00:10<00:36, 4.96it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 8%|▊ | 16/195 [00:10<00:36, 4.96it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 8%|▊ | 16/195 [00:10<00:36, 4.96it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 8%|▊ | 16/195 [00:10<00:36, 4.96it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 8%|▊ | 16/195 [00:10<00:36, 4.96it/s] 9%|▉ | 18/195 [00:10<00:28, 6.19it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.24.ln.weight", shape: (3072,), dtype: float32 9%|▉ | 18/195 [00:10<00:28, 6.19it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 9%|▉ | 18/195 [00:10<00:28, 6.19it/s] [2024-06-11 04:34:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 9%|▉ | 18/195 [00:10<00:28, 6.19it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 9%|▉ | 18/195 [00:10<00:28, 6.19it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 9%|▉ | 18/195 [00:11<00:28, 6.19it/s] 11%|█ | 21/195 [00:11<00:21, 8.28it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.24.post_attention_layernorm.weight", shape: (3072,), dtype: float32 11%|█ | 21/195 [00:11<00:21, 8.28it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 11%|█ | 21/195 [00:11<00:21, 8.28it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 11%|█ | 21/195 [00:11<00:21, 8.28it/s] 12%|█▏ | 23/195 [00:11<00:18, 9.51it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 12%|█▏ | 23/195 [00:11<00:18, 9.51it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 12%|█▏ | 23/195 [00:11<00:18, 9.51it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.25.ln.weight", shape: (3072,), dtype: float32 12%|█▏ | 23/195 [00:11<00:18, 9.51it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 12%|█▏ | 23/195 [00:11<00:18, 9.51it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 12%|█▏ | 23/195 [00:11<00:18, 9.51it/s] 13%|█▎ | 26/195 [00:11<00:13, 12.25it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 13%|█▎ | 26/195 [00:11<00:13, 12.25it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 13%|█▎ | 26/195 [00:11<00:13, 12.25it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.25.post_attention_layernorm.weight", shape: (3072,), dtype: float32 13%|█▎ | 26/195 [00:11<00:13, 12.25it/s] 14%|█▍ | 28/195 [00:11<00:12, 12.95it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 14%|█▍ | 28/195 [00:11<00:12, 12.95it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 14%|█▍ | 28/195 [00:11<00:12, 12.95it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 14%|█▍ | 28/195 [00:11<00:12, 12.95it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 14%|█▍ | 28/195 [00:11<00:12, 12.95it/s] 15%|█▌ | 30/195 [00:11<00:11, 13.76it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.26.ln.weight", shape: (3072,), dtype: float32 15%|█▌ | 30/195 [00:11<00:11, 13.76it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 15%|█▌ | 30/195 [00:11<00:11, 13.76it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 15%|█▌ | 30/195 [00:11<00:11, 13.76it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 15%|█▌ | 30/195 [00:11<00:11, 13.76it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 15%|█▌ | 30/195 [00:11<00:11, 13.76it/s] 17%|█▋ | 33/195 [00:11<00:10, 15.39it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.26.post_attention_layernorm.weight", shape: (3072,), dtype: float32 17%|█▋ | 33/195 [00:11<00:10, 15.39it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 17%|█▋ | 33/195 [00:11<00:10, 15.39it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 17%|█▋ | 33/195 [00:11<00:10, 15.39it/s] 18%|█▊ | 35/195 [00:11<00:10, 15.44it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 18%|█▊ | 35/195 [00:11<00:10, 15.44it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 18%|█▊ | 35/195 [00:11<00:10, 15.44it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.27.ln.weight", shape: (3072,), dtype: float32 18%|█▊ | 35/195 [00:11<00:10, 15.44it/s] [2024-06-11 04:34:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 18%|█▊ | 35/195 [00:11<00:10, 15.44it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 18%|█▊ | 35/195 [00:11<00:10, 15.44it/s] 19%|█▉ | 38/195 [00:11<00:08, 18.04it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 19%|█▉ | 38/195 [00:11<00:08, 18.04it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 19%|█▉ | 38/195 [00:12<00:08, 18.04it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.27.post_attention_layernorm.weight", shape: (3072,), dtype: float32 19%|█▉ | 38/195 [00:12<00:08, 18.04it/s] 21%|██ | 40/195 [00:12<00:08, 17.31it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 21%|██ | 40/195 [00:12<00:08, 17.31it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 21%|██ | 40/195 [00:12<00:08, 17.31it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 21%|██ | 40/195 [00:12<00:08, 17.31it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 21%|██ | 40/195 [00:12<00:08, 17.31it/s] 22%|██▏ | 42/195 [00:12<00:08, 17.14it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.28.ln.weight", shape: (3072,), dtype: float32 22%|██▏ | 42/195 [00:12<00:08, 17.14it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 22%|██▏ | 42/195 [00:12<00:08, 17.14it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 22%|██▏ | 42/195 [00:12<00:08, 17.14it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 22%|██▏ | 42/195 [00:12<00:08, 17.14it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 22%|██▏ | 42/195 [00:12<00:08, 17.14it/s] 23%|██▎ | 45/195 [00:12<00:08, 17.95it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.28.post_attention_layernorm.weight", shape: (3072,), dtype: float32 23%|██▎ | 45/195 [00:12<00:08, 17.95it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 23%|██▎ | 45/195 [00:12<00:08, 17.95it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 23%|██▎ | 45/195 [00:12<00:08, 17.95it/s] 24%|██▍ | 47/195 [00:12<00:08, 17.39it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 24%|██▍ | 47/195 [00:12<00:08, 17.39it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 24%|██▍ | 47/195 [00:12<00:08, 17.39it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.29.ln.weight", shape: (3072,), dtype: float32 24%|██▍ | 47/195 [00:12<00:08, 17.39it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 24%|██▍ | 47/195 [00:12<00:08, 17.39it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 24%|██▍ | 47/195 [00:12<00:08, 17.39it/s] 26%|██▌ | 50/195 [00:12<00:07, 19.43it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 26%|██▌ | 50/195 [00:12<00:07, 19.43it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 26%|██▌ | 50/195 [00:12<00:07, 19.43it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.29.post_attention_layernorm.weight", shape: (3072,), dtype: float32 26%|██▌ | 50/195 [00:12<00:07, 19.43it/s] 27%|██▋ | 52/195 [00:12<00:07, 18.27it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 27%|██▋ | 52/195 [00:12<00:07, 18.27it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 27%|██▋ | 52/195 [00:12<00:07, 18.27it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 27%|██▋ | 52/195 [00:12<00:07, 18.27it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 27%|██▋ | 52/195 [00:12<00:07, 18.27it/s] 28%|██▊ | 54/195 [00:12<00:07, 17.83it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.30.ln.weight", shape: (3072,), dtype: float32 28%|██▊ | 54/195 [00:12<00:07, 17.83it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 28%|██▊ | 54/195 [00:12<00:07, 17.83it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 28%|██▊ | 54/195 [00:12<00:07, 17.83it/s] [2024-06-11 04:34:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 28%|██▊ | 54/195 [00:12<00:07, 17.83it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 28%|██▊ | 54/195 [00:12<00:07, 17.83it/s] 29%|██▉ | 57/195 [00:12<00:07, 18.40it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.30.post_attention_layernorm.weight", shape: (3072,), dtype: float32 29%|██▉ | 57/195 [00:12<00:07, 18.40it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 29%|██▉ | 57/195 [00:12<00:07, 18.40it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 29%|██▉ | 57/195 [00:13<00:07, 18.40it/s] 30%|███ | 59/195 [00:13<00:07, 17.71it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 30%|███ | 59/195 [00:13<00:07, 17.71it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 30%|███ | 59/195 [00:13<00:07, 17.71it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.31.ln.weight", shape: (3072,), dtype: float32 30%|███ | 59/195 [00:13<00:07, 17.71it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 30%|███ | 59/195 [00:13<00:07, 17.71it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 30%|███ | 59/195 [00:13<00:07, 17.71it/s] 32%|███▏ | 62/195 [00:13<00:06, 19.62it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 32%|███▏ | 62/195 [00:13<00:06, 19.62it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 32%|███▏ | 62/195 [00:13<00:06, 19.62it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.31.post_attention_layernorm.weight", shape: (3072,), dtype: float32 32%|███▏ | 62/195 [00:13<00:06, 19.62it/s] 33%|███▎ | 64/195 [00:13<00:07, 18.33it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 33%|███▎ | 64/195 [00:13<00:07, 18.33it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 33%|███▎ | 64/195 [00:13<00:07, 18.33it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 33%|███▎ | 64/195 [00:13<00:07, 18.33it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 33%|███▎ | 64/195 [00:13<00:07, 18.33it/s] 34%|███▍ | 66/195 [00:13<00:07, 17.94it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.norm.weight", shape: (3072,), dtype: float32 34%|███▍ | 66/195 [00:13<00:07, 17.94it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:197: Unloading HF weight file: /ssd2/models/Phi-3-mini-128k-instruct/model-00002-of-00002.safetensors 34%|███▍ | 66/195 [00:13<00:07, 17.94it/s] [2024-06-11 04:34:39] INFO huggingface_loader.py:185: Loading HF parameters from: /ssd2/models/Phi-3-mini-128k-instruct/model-00001-of-00002.safetensors 34%|███▍ | 66/195 [00:13<00:07, 17.94it/s] 34%|███▍ | 67/195 [00:19<00:36, 3.52it/s] Traceback (most recent call last): File "", line 198, in _run_module_as_main File "", line 88, in _run_code File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/__main__.py", line 64, in main() File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/__main__.py", line 37, in main cli.main(sys.argv[2:]) File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/cli/convert_weight.py", line 88, in main convert_weight( File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/interface/convert_weight.py", line 181, in convert_weight _convert_args(args) File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/interface/convert_weight.py", line 145, in _convert_args tvmjs.dump_ndarray_cache( File "/ssd1/rickzhou/tvm/python/tvm/contrib/tvmjs.py", line 272, in dump_ndarray_cache for k, origin_v in param_generator: File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/interface/convert_weight.py", line 129, in _param_generator for name, param in loader.load(device=args.device, preshard_funcs=preshard_funcs): File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/loader/huggingface_loader.py", line 118, in load param = self._load_mlc_param(mlc_name, device=device) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/loader/huggingface_loader.py", line 150, in _load_mlc_param self._load_file(path) File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/loader/huggingface_loader.py", line 189, in _load_file for name, param in load_func(path): File "/ssd1/rickzhou/mlc-llm/python/mlc_llm/loader/utils.py", line 65, in load_safetensor_shard param = param.float() ^^^^^^^^^^^^^ KeyboardInterrupt /home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm gen_config /ssd2/models/Phi-3-mini-128k-instruct --quantization q4f32_1 --conv-template phi-3 --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC [2024-06-11 04:37:27] INFO auto_config.py:116: Found model configuration: /ssd2/models/Phi-3-mini-128k-instruct/config.json [2024-06-11 04:37:27] INFO auto_config.py:154: Found model type: phi3. Use `--model-type` to override. [2024-06-11 04:37:27] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072) [2024-06-11 04:37:27] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048 [2024-06-11 04:37:27] INFO config.py:107: Overriding max_batch_size from 1 to 80 [2024-06-11 04:37:27] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 1 [2024-06-11 04:37:27] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [32000, 32001, 32007] [2024-06-11 04:37:27] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 32000 [2024-06-11 04:37:27] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/tokenizer.model. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer.model [2024-06-11 04:37:27] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer.json [2024-06-11 04:37:27] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/vocab.json [2024-06-11 04:37:27] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/merges.txt [2024-06-11 04:37:27] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/added_tokens.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/added_tokens.json [2024-06-11 04:37:27] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer_config.json [2024-06-11 04:37:27] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_fallback', 'prepend_space_in_encode': True, 'strip_space_in_decode': True} [2024-06-11 04:37:27] INFO gen_config.py:32: [System default] Setting temperature: 1.0 [2024-06-11 04:37:27] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0 [2024-06-11 04:37:27] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0 [2024-06-11 04:37:27] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0 [2024-06-11 04:37:27] INFO gen_config.py:32: [System default] Setting top_p: 1.0 [2024-06-11 04:37:27] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/mlc-chat-config.json /home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm convert_weight /ssd2/models/Phi-3-mini-128k-instruct --quantization q4f32_1 --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC [2024-06-11 04:37:29] INFO auto_config.py:116: Found model configuration: /ssd2/models/Phi-3-mini-128k-instruct/config.json [2024-06-11 04:37:30] INFO auto_device.py:79: Found device: cuda:0 [2024-06-11 04:37:30] INFO auto_device.py:79: Found device: cuda:1 [2024-06-11 04:37:31] INFO auto_device.py:88: Not found device: rocm:0 [2024-06-11 04:37:32] INFO auto_device.py:88: Not found device: metal:0 [2024-06-11 04:37:33] INFO auto_device.py:79: Found device: vulkan:0 [2024-06-11 04:37:33] INFO auto_device.py:79: Found device: vulkan:1 [2024-06-11 04:37:33] INFO auto_device.py:79: Found device: vulkan:2 [2024-06-11 04:37:34] INFO auto_device.py:88: Not found device: opencl:0 [2024-06-11 04:37:34] INFO auto_device.py:35: Using device: cuda:0 [2024-06-11 04:37:34] INFO auto_weight.py:71: Finding weights in: /ssd2/models/Phi-3-mini-128k-instruct [2024-06-11 04:37:34] INFO auto_weight.py:137: Not found Huggingface PyTorch [2024-06-11 04:37:34] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /ssd2/models/Phi-3-mini-128k-instruct/model.safetensors.index.json [2024-06-11 04:37:34] INFO auto_weight.py:107: Using source weight configuration: /ssd2/models/Phi-3-mini-128k-instruct/model.safetensors.index.json. Use `--source` to override. [2024-06-11 04:37:34] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override. [2024-06-11 04:37:34] INFO auto_config.py:154: Found model type: phi3. Use `--model-type` to override. [2024-06-11 04:37:34] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072) [2024-06-11 04:37:34] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048 Weight conversion with arguments: --config /ssd2/models/Phi-3-mini-128k-instruct/config.json --quantization GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7) --model-type phi3 --device cuda:0 --source /ssd2/models/Phi-3-mini-128k-instruct/model.safetensors.index.json --source-format huggingface-safetensor --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC Start storing to cache /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC 0%| | 0/195 [00:00 type is zero. setattr(self, word, getattr(machar, word).flat[0]) /home/rickzhou/miniconda3/envs/mlc/lib/python3.11/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) 1%| | 1/195 [00:02<09:08, 2.83s/it] [2024-06-11 04:37:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.21.ln.weight", shape: (3072,), dtype: float32 1%| | 1/195 [00:02<09:08, 2.83s/it] [2024-06-11 04:37:40] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 8192), float32, cuda, axis=1, output_transpose=False) 1%| | 1/195 [00:02<09:08, 2.83s/it] [2024-06-11 04:37:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 1%| | 1/195 [00:03<09:08, 2.83s/it] [2024-06-11 04:37:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 1%| | 1/195 [00:03<09:08, 2.83s/it] 2%|▏ | 3/195 [00:03<02:43, 1.17it/s] [2024-06-11 04:37:40] INFO group_quantization.py:217: Compiling quantize function for key: ((16384, 3072), float32, cuda, axis=1, output_transpose=False) 2%|▏ | 3/195 [00:03<02:43, 1.17it/s] [2024-06-11 04:37:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 2%|▏ | 3/195 [00:03<02:43, 1.17it/s] [2024-06-11 04:37:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 2%|▏ | 3/195 [00:03<02:43, 1.17it/s] 2%|▏ | 4/195 [00:03<02:15, 1.41it/s] [2024-06-11 04:37:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.21.post_attention_layernorm.weight", shape: (3072,), dtype: float32 2%|▏ | 4/195 [00:03<02:15, 1.41it/s] [2024-06-11 04:37:41] INFO group_quantization.py:217: Compiling quantize function for key: ((9216, 3072), float32, cuda, axis=1, output_transpose=False) 2%|▏ | 4/195 [00:03<02:15, 1.41it/s] [2024-06-11 04:37:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 2%|▏ | 4/195 [00:03<02:15, 1.41it/s] [2024-06-11 04:37:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 2%|▏ | 4/195 [00:04<02:15, 1.41it/s] 3%|▎ | 6/195 [00:04<01:27, 2.17it/s] [2024-06-11 04:37:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.22.ln.weight", shape: (3072,), dtype: float32 3%|▎ | 6/195 [00:04<01:27, 2.17it/s] [2024-06-11 04:37:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 3%|▎ | 6/195 [00:04<01:27, 2.17it/s] [2024-06-11 04:37:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 3%|▎ | 6/195 [00:04<01:27, 2.17it/s] [2024-06-11 04:37:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 3%|▎ | 6/195 [00:04<01:27, 2.17it/s] [2024-06-11 04:37:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 3%|▎ | 6/195 [00:04<01:27, 2.17it/s] 5%|▍ | 9/195 [00:04<00:47, 3.93it/s] [2024-06-11 04:37:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.22.post_attention_layernorm.weight", shape: (3072,), dtype: float32 5%|▍ | 9/195 [00:04<00:47, 3.93it/s] [2024-06-11 04:37:41] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 3072), float32, cuda, axis=1, output_transpose=False) 5%|▍ | 9/195 [00:04<00:47, 3.93it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 5%|▍ | 9/195 [00:04<00:47, 3.93it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 5%|▍ | 9/195 [00:04<00:47, 3.93it/s] 6%|▌ | 11/195 [00:04<00:44, 4.17it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 6%|▌ | 11/195 [00:04<00:44, 4.17it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 6%|▌ | 11/195 [00:04<00:44, 4.17it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.23.ln.weight", shape: (3072,), dtype: float32 6%|▌ | 11/195 [00:04<00:44, 4.17it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 6%|▌ | 11/195 [00:04<00:44, 4.17it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 6%|▌ | 11/195 [00:04<00:44, 4.17it/s] 7%|▋ | 14/195 [00:04<00:28, 6.29it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 7%|▋ | 14/195 [00:04<00:28, 6.29it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 7%|▋ | 14/195 [00:04<00:28, 6.29it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.23.post_attention_layernorm.weight", shape: (3072,), dtype: float32 7%|▋ | 14/195 [00:04<00:28, 6.29it/s] 8%|▊ | 16/195 [00:04<00:24, 7.43it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 8%|▊ | 16/195 [00:04<00:24, 7.43it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 8%|▊ | 16/195 [00:04<00:24, 7.43it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 8%|▊ | 16/195 [00:04<00:24, 7.43it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 8%|▊ | 16/195 [00:05<00:24, 7.43it/s] 9%|▉ | 18/195 [00:05<00:19, 8.88it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.24.ln.weight", shape: (3072,), dtype: float32 9%|▉ | 18/195 [00:05<00:19, 8.88it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 9%|▉ | 18/195 [00:05<00:19, 8.88it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 9%|▉ | 18/195 [00:05<00:19, 8.88it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 9%|▉ | 18/195 [00:05<00:19, 8.88it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 9%|▉ | 18/195 [00:05<00:19, 8.88it/s] 11%|█ | 21/195 [00:05<00:15, 10.95it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.24.post_attention_layernorm.weight", shape: (3072,), dtype: float32 11%|█ | 21/195 [00:05<00:15, 10.95it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 11%|█ | 21/195 [00:05<00:15, 10.95it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 11%|█ | 21/195 [00:05<00:15, 10.95it/s] 12%|█▏ | 23/195 [00:05<00:14, 11.92it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 12%|█▏ | 23/195 [00:05<00:14, 11.92it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 12%|█▏ | 23/195 [00:05<00:14, 11.92it/s] [2024-06-11 04:37:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.25.ln.weight", shape: (3072,), dtype: float32 12%|█▏ | 23/195 [00:05<00:14, 11.92it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 12%|█▏ | 23/195 [00:05<00:14, 11.92it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 12%|█▏ | 23/195 [00:05<00:14, 11.92it/s] 13%|█▎ | 26/195 [00:05<00:11, 14.48it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 13%|█▎ | 26/195 [00:05<00:11, 14.48it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 13%|█▎ | 26/195 [00:05<00:11, 14.48it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.25.post_attention_layernorm.weight", shape: (3072,), dtype: float32 13%|█▎ | 26/195 [00:05<00:11, 14.48it/s] 14%|█▍ | 28/195 [00:05<00:11, 14.64it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 14%|█▍ | 28/195 [00:05<00:11, 14.64it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 14%|█▍ | 28/195 [00:05<00:11, 14.64it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 14%|█▍ | 28/195 [00:05<00:11, 14.64it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 14%|█▍ | 28/195 [00:05<00:11, 14.64it/s] 15%|█▌ | 30/195 [00:05<00:10, 15.47it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.26.ln.weight", shape: (3072,), dtype: float32 15%|█▌ | 30/195 [00:05<00:10, 15.47it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 15%|█▌ | 30/195 [00:05<00:10, 15.47it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 15%|█▌ | 30/195 [00:05<00:10, 15.47it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 15%|█▌ | 30/195 [00:05<00:10, 15.47it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 15%|█▌ | 30/195 [00:05<00:10, 15.47it/s] 17%|█▋ | 33/195 [00:05<00:09, 16.38it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.26.post_attention_layernorm.weight", shape: (3072,), dtype: float32 17%|█▋ | 33/195 [00:05<00:09, 16.38it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 17%|█▋ | 33/195 [00:05<00:09, 16.38it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 17%|█▋ | 33/195 [00:05<00:09, 16.38it/s] 18%|█▊ | 35/195 [00:05<00:09, 16.09it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 18%|█▊ | 35/195 [00:05<00:09, 16.09it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 18%|█▊ | 35/195 [00:05<00:09, 16.09it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.27.ln.weight", shape: (3072,), dtype: float32 18%|█▊ | 35/195 [00:05<00:09, 16.09it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 18%|█▊ | 35/195 [00:06<00:09, 16.09it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 18%|█▊ | 35/195 [00:06<00:09, 16.09it/s] 19%|█▉ | 38/195 [00:06<00:08, 18.13it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 19%|█▉ | 38/195 [00:06<00:08, 18.13it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 19%|█▉ | 38/195 [00:06<00:08, 18.13it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.27.post_attention_layernorm.weight", shape: (3072,), dtype: float32 19%|█▉ | 38/195 [00:06<00:08, 18.13it/s] 21%|██ | 40/195 [00:06<00:09, 17.09it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 21%|██ | 40/195 [00:06<00:09, 17.09it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 21%|██ | 40/195 [00:06<00:09, 17.09it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 21%|██ | 40/195 [00:06<00:09, 17.09it/s] [2024-06-11 04:37:43] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 21%|██ | 40/195 [00:06<00:09, 17.09it/s] 22%|██▏ | 42/195 [00:06<00:08, 17.24it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.28.ln.weight", shape: (3072,), dtype: float32 22%|██▏ | 42/195 [00:06<00:08, 17.24it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 22%|██▏ | 42/195 [00:06<00:08, 17.24it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 22%|██▏ | 42/195 [00:06<00:08, 17.24it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 22%|██▏ | 42/195 [00:06<00:08, 17.24it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 22%|██▏ | 42/195 [00:06<00:08, 17.24it/s] 23%|██▎ | 45/195 [00:06<00:08, 16.79it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.28.post_attention_layernorm.weight", shape: (3072,), dtype: float32 23%|██▎ | 45/195 [00:06<00:08, 16.79it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 23%|██▎ | 45/195 [00:06<00:08, 16.79it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 23%|██▎ | 45/195 [00:06<00:08, 16.79it/s] 24%|██▍ | 47/195 [00:06<00:09, 16.28it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 24%|██▍ | 47/195 [00:06<00:09, 16.28it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 24%|██▍ | 47/195 [00:06<00:09, 16.28it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.29.ln.weight", shape: (3072,), dtype: float32 24%|██▍ | 47/195 [00:06<00:09, 16.28it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 24%|██▍ | 47/195 [00:06<00:09, 16.28it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 24%|██▍ | 47/195 [00:06<00:09, 16.28it/s] 26%|██▌ | 50/195 [00:06<00:07, 18.25it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 26%|██▌ | 50/195 [00:06<00:07, 18.25it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 26%|██▌ | 50/195 [00:06<00:07, 18.25it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.29.post_attention_layernorm.weight", shape: (3072,), dtype: float32 26%|██▌ | 50/195 [00:06<00:07, 18.25it/s] 27%|██▋ | 52/195 [00:06<00:08, 17.16it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 27%|██▋ | 52/195 [00:06<00:08, 17.16it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 27%|██▋ | 52/195 [00:06<00:08, 17.16it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 27%|██▋ | 52/195 [00:06<00:08, 17.16it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 27%|██▋ | 52/195 [00:07<00:08, 17.16it/s] 28%|██▊ | 54/195 [00:07<00:08, 17.29it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.30.ln.weight", shape: (3072,), dtype: float32 28%|██▊ | 54/195 [00:07<00:08, 17.29it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 28%|██▊ | 54/195 [00:07<00:08, 17.29it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 28%|██▊ | 54/195 [00:07<00:08, 17.29it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 28%|██▊ | 54/195 [00:07<00:08, 17.29it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 28%|██▊ | 54/195 [00:07<00:08, 17.29it/s] 29%|██▉ | 57/195 [00:07<00:07, 17.70it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.30.post_attention_layernorm.weight", shape: (3072,), dtype: float32 29%|██▉ | 57/195 [00:07<00:07, 17.70it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 29%|██▉ | 57/195 [00:07<00:07, 17.70it/s] [2024-06-11 04:37:44] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 29%|██▉ | 57/195 [00:07<00:07, 17.70it/s] 30%|███ | 59/195 [00:07<00:07, 17.09it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 30%|███ | 59/195 [00:07<00:07, 17.09it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 30%|███ | 59/195 [00:07<00:07, 17.09it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.31.ln.weight", shape: (3072,), dtype: float32 30%|███ | 59/195 [00:07<00:07, 17.09it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 30%|███ | 59/195 [00:07<00:07, 17.09it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 30%|███ | 59/195 [00:07<00:07, 17.09it/s] 32%|███▏ | 62/195 [00:07<00:06, 19.09it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 32%|███▏ | 62/195 [00:07<00:06, 19.09it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 32%|███▏ | 62/195 [00:07<00:06, 19.09it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.31.post_attention_layernorm.weight", shape: (3072,), dtype: float32 32%|███▏ | 62/195 [00:07<00:06, 19.09it/s] 33%|███▎ | 64/195 [00:07<00:07, 17.79it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 33%|███▎ | 64/195 [00:07<00:07, 17.79it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 33%|███▎ | 64/195 [00:07<00:07, 17.79it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 33%|███▎ | 64/195 [00:07<00:07, 17.79it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 33%|███▎ | 64/195 [00:07<00:07, 17.79it/s] 34%|███▍ | 66/195 [00:07<00:07, 17.82it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.norm.weight", shape: (3072,), dtype: float32 34%|███▍ | 66/195 [00:07<00:07, 17.82it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:197: Unloading HF weight file: /ssd2/models/Phi-3-mini-128k-instruct/model-00002-of-00002.safetensors 34%|███▍ | 66/195 [00:07<00:07, 17.82it/s] [2024-06-11 04:37:45] INFO huggingface_loader.py:185: Loading HF parameters from: /ssd2/models/Phi-3-mini-128k-instruct/model-00001-of-00002.safetensors 34%|███▍ | 66/195 [00:07<00:07, 17.82it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.embd.q_weight", shape: (32064, 384), dtype: uint32 34%|███▍ | 66/195 [00:08<00:07, 17.82it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.embd.q_scale", shape: (32064, 96), dtype: float32 34%|███▍ | 66/195 [00:08<00:07, 17.82it/s] 35%|███▍ | 68/195 [00:08<00:26, 4.73it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.0.ln.weight", shape: (3072,), dtype: float32 35%|███▍ | 68/195 [00:08<00:26, 4.73it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 35%|███▍ | 68/195 [00:08<00:26, 4.73it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 35%|███▍ | 68/195 [00:09<00:26, 4.73it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 35%|███▍ | 68/195 [00:09<00:26, 4.73it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 35%|███▍ | 68/195 [00:09<00:26, 4.73it/s] 36%|███▋ | 71/195 [00:09<00:20, 6.17it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.0.post_attention_layernorm.weight", shape: (3072,), dtype: float32 36%|███▋ | 71/195 [00:09<00:20, 6.17it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 36%|███▋ | 71/195 [00:09<00:20, 6.17it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 36%|███▋ | 71/195 [00:09<00:20, 6.17it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 36%|███▋ | 71/195 [00:09<00:20, 6.17it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 36%|███▋ | 71/195 [00:09<00:20, 6.17it/s] 38%|███▊ | 74/195 [00:09<00:14, 8.41it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.1.ln.weight", shape: (3072,), dtype: float32 38%|███▊ | 74/195 [00:09<00:14, 8.41it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 38%|███▊ | 74/195 [00:09<00:14, 8.41it/s] [2024-06-11 04:37:46] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 38%|███▊ | 74/195 [00:09<00:14, 8.41it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 38%|███▊ | 74/195 [00:09<00:14, 8.41it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 38%|███▊ | 74/195 [00:09<00:14, 8.41it/s] 39%|███▉ | 77/195 [00:09<00:11, 10.09it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.1.post_attention_layernorm.weight", shape: (3072,), dtype: float32 39%|███▉ | 77/195 [00:09<00:11, 10.09it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 39%|███▉ | 77/195 [00:09<00:11, 10.09it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 39%|███▉ | 77/195 [00:09<00:11, 10.09it/s] 41%|████ | 79/195 [00:09<00:10, 11.07it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 41%|████ | 79/195 [00:09<00:10, 11.07it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 41%|████ | 79/195 [00:09<00:10, 11.07it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.10.ln.weight", shape: (3072,), dtype: float32 41%|████ | 79/195 [00:09<00:10, 11.07it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 41%|████ | 79/195 [00:09<00:10, 11.07it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 41%|████ | 79/195 [00:09<00:10, 11.07it/s] 42%|████▏ | 82/195 [00:09<00:08, 13.69it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 42%|████▏ | 82/195 [00:09<00:08, 13.69it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 42%|████▏ | 82/195 [00:09<00:08, 13.69it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.10.post_attention_layernorm.weight", shape: (3072,), dtype: float32 42%|████▏ | 82/195 [00:09<00:08, 13.69it/s] 43%|████▎ | 84/195 [00:09<00:07, 14.22it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 43%|████▎ | 84/195 [00:09<00:07, 14.22it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 43%|████▎ | 84/195 [00:09<00:07, 14.22it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 43%|████▎ | 84/195 [00:09<00:07, 14.22it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 43%|████▎ | 84/195 [00:09<00:07, 14.22it/s] 44%|████▍ | 86/195 [00:09<00:07, 15.15it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.11.ln.weight", shape: (3072,), dtype: float32 44%|████▍ | 86/195 [00:09<00:07, 15.15it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 44%|████▍ | 86/195 [00:09<00:07, 15.15it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 44%|████▍ | 86/195 [00:09<00:07, 15.15it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 44%|████▍ | 86/195 [00:10<00:07, 15.15it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 44%|████▍ | 86/195 [00:10<00:07, 15.15it/s] 46%|████▌ | 89/195 [00:10<00:06, 15.60it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.11.post_attention_layernorm.weight", shape: (3072,), dtype: float32 46%|████▌ | 89/195 [00:10<00:06, 15.60it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 46%|████▌ | 89/195 [00:10<00:06, 15.60it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 46%|████▌ | 89/195 [00:10<00:06, 15.60it/s] 47%|████▋ | 91/195 [00:10<00:06, 15.27it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 47%|████▋ | 91/195 [00:10<00:06, 15.27it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 47%|████▋ | 91/195 [00:10<00:06, 15.27it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.12.ln.weight", shape: (3072,), dtype: float32 47%|████▋ | 91/195 [00:10<00:06, 15.27it/s] [2024-06-11 04:37:47] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 47%|████▋ | 91/195 [00:10<00:06, 15.27it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 47%|████▋ | 91/195 [00:10<00:06, 15.27it/s] 48%|████▊ | 94/195 [00:10<00:05, 17.64it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 48%|████▊ | 94/195 [00:10<00:05, 17.64it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 48%|████▊ | 94/195 [00:10<00:05, 17.64it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.12.post_attention_layernorm.weight", shape: (3072,), dtype: float32 48%|████▊ | 94/195 [00:10<00:05, 17.64it/s] 49%|████▉ | 96/195 [00:10<00:05, 17.07it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 49%|████▉ | 96/195 [00:10<00:05, 17.07it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 49%|████▉ | 96/195 [00:10<00:05, 17.07it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 49%|████▉ | 96/195 [00:10<00:05, 17.07it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 49%|████▉ | 96/195 [00:10<00:05, 17.07it/s] 50%|█████ | 98/195 [00:10<00:05, 17.22it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.13.ln.weight", shape: (3072,), dtype: float32 50%|█████ | 98/195 [00:10<00:05, 17.22it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 50%|█████ | 98/195 [00:10<00:05, 17.22it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 50%|█████ | 98/195 [00:10<00:05, 17.22it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 50%|█████ | 98/195 [00:10<00:05, 17.22it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 50%|█████ | 98/195 [00:10<00:05, 17.22it/s] 52%|█████▏ | 101/195 [00:10<00:05, 16.89it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.13.post_attention_layernorm.weight", shape: (3072,), dtype: float32 52%|█████▏ | 101/195 [00:10<00:05, 16.89it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 52%|█████▏ | 101/195 [00:10<00:05, 16.89it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 52%|█████▏ | 101/195 [00:10<00:05, 16.89it/s] 53%|█████▎ | 103/195 [00:10<00:05, 16.28it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 53%|█████▎ | 103/195 [00:10<00:05, 16.28it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 53%|█████▎ | 103/195 [00:10<00:05, 16.28it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.14.ln.weight", shape: (3072,), dtype: float32 53%|█████▎ | 103/195 [00:10<00:05, 16.28it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 53%|█████▎ | 103/195 [00:11<00:05, 16.28it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 53%|█████▎ | 103/195 [00:11<00:05, 16.28it/s] 54%|█████▍ | 106/195 [00:11<00:04, 18.55it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 54%|█████▍ | 106/195 [00:11<00:04, 18.55it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 54%|█████▍ | 106/195 [00:11<00:04, 18.55it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.14.post_attention_layernorm.weight", shape: (3072,), dtype: float32 54%|█████▍ | 106/195 [00:11<00:04, 18.55it/s] 55%|█████▌ | 108/195 [00:11<00:04, 17.92it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 55%|█████▌ | 108/195 [00:11<00:04, 17.92it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 55%|█████▌ | 108/195 [00:11<00:04, 17.92it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 55%|█████▌ | 108/195 [00:11<00:04, 17.92it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 55%|█████▌ | 108/195 [00:11<00:04, 17.92it/s] 56%|█████▋ | 110/195 [00:11<00:04, 18.10it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.15.ln.weight", shape: (3072,), dtype: float32 56%|█████▋ | 110/195 [00:11<00:04, 18.10it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 56%|█████▋ | 110/195 [00:11<00:04, 18.10it/s] [2024-06-11 04:37:48] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 56%|█████▋ | 110/195 [00:11<00:04, 18.10it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 56%|█████▋ | 110/195 [00:11<00:04, 18.10it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 56%|█████▋ | 110/195 [00:11<00:04, 18.10it/s] 58%|█████▊ | 113/195 [00:11<00:04, 17.44it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.15.post_attention_layernorm.weight", shape: (3072,), dtype: float32 58%|█████▊ | 113/195 [00:11<00:04, 17.44it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 58%|█████▊ | 113/195 [00:11<00:04, 17.44it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 58%|█████▊ | 113/195 [00:11<00:04, 17.44it/s] 59%|█████▉ | 115/195 [00:11<00:04, 16.64it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 59%|█████▉ | 115/195 [00:11<00:04, 16.64it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 59%|█████▉ | 115/195 [00:11<00:04, 16.64it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.16.ln.weight", shape: (3072,), dtype: float32 59%|█████▉ | 115/195 [00:11<00:04, 16.64it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 59%|█████▉ | 115/195 [00:11<00:04, 16.64it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 59%|█████▉ | 115/195 [00:11<00:04, 16.64it/s] 61%|██████ | 118/195 [00:11<00:04, 18.65it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 61%|██████ | 118/195 [00:11<00:04, 18.65it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 61%|██████ | 118/195 [00:11<00:04, 18.65it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.16.post_attention_layernorm.weight", shape: (3072,), dtype: float32 61%|██████ | 118/195 [00:11<00:04, 18.65it/s] 62%|██████▏ | 120/195 [00:11<00:04, 18.15it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 62%|██████▏ | 120/195 [00:11<00:04, 18.15it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 62%|██████▏ | 120/195 [00:11<00:04, 18.15it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 62%|██████▏ | 120/195 [00:11<00:04, 18.15it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 62%|██████▏ | 120/195 [00:11<00:04, 18.15it/s] 63%|██████▎ | 122/195 [00:11<00:04, 18.02it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.17.ln.weight", shape: (3072,), dtype: float32 63%|██████▎ | 122/195 [00:11<00:04, 18.02it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 63%|██████▎ | 122/195 [00:11<00:04, 18.02it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 63%|██████▎ | 122/195 [00:12<00:04, 18.02it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 63%|██████▎ | 122/195 [00:12<00:04, 18.02it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 63%|██████▎ | 122/195 [00:12<00:04, 18.02it/s] 64%|██████▍ | 125/195 [00:12<00:03, 17.55it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.17.post_attention_layernorm.weight", shape: (3072,), dtype: float32 64%|██████▍ | 125/195 [00:12<00:03, 17.55it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 64%|██████▍ | 125/195 [00:12<00:03, 17.55it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 64%|██████▍ | 125/195 [00:12<00:03, 17.55it/s] 65%|██████▌ | 127/195 [00:12<00:03, 17.05it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 65%|██████▌ | 127/195 [00:12<00:03, 17.05it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 65%|██████▌ | 127/195 [00:12<00:03, 17.05it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.18.ln.weight", shape: (3072,), dtype: float32 65%|██████▌ | 127/195 [00:12<00:03, 17.05it/s] [2024-06-11 04:37:49] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 65%|██████▌ | 127/195 [00:12<00:03, 17.05it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 65%|██████▌ | 127/195 [00:12<00:03, 17.05it/s] 67%|██████▋ | 130/195 [00:12<00:03, 19.12it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 67%|██████▋ | 130/195 [00:12<00:03, 19.12it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 67%|██████▋ | 130/195 [00:12<00:03, 19.12it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.18.post_attention_layernorm.weight", shape: (3072,), dtype: float32 67%|██████▋ | 130/195 [00:12<00:03, 19.12it/s] 68%|██████▊ | 132/195 [00:12<00:03, 18.22it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 68%|██████▊ | 132/195 [00:12<00:03, 18.22it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 68%|██████▊ | 132/195 [00:12<00:03, 18.22it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 68%|██████▊ | 132/195 [00:12<00:03, 18.22it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 68%|██████▊ | 132/195 [00:12<00:03, 18.22it/s] 69%|██████▊ | 134/195 [00:12<00:03, 18.32it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.19.ln.weight", shape: (3072,), dtype: float32 69%|██████▊ | 134/195 [00:12<00:03, 18.32it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 69%|██████▊ | 134/195 [00:12<00:03, 18.32it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 69%|██████▊ | 134/195 [00:12<00:03, 18.32it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 69%|██████▊ | 134/195 [00:12<00:03, 18.32it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 69%|██████▊ | 134/195 [00:12<00:03, 18.32it/s] 70%|███████ | 137/195 [00:12<00:03, 17.84it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.19.post_attention_layernorm.weight", shape: (3072,), dtype: float32 70%|███████ | 137/195 [00:12<00:03, 17.84it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 70%|███████ | 137/195 [00:12<00:03, 17.84it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 70%|███████ | 137/195 [00:12<00:03, 17.84it/s] 71%|███████▏ | 139/195 [00:12<00:03, 17.25it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 71%|███████▏ | 139/195 [00:12<00:03, 17.25it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 71%|███████▏ | 139/195 [00:12<00:03, 17.25it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.2.ln.weight", shape: (3072,), dtype: float32 71%|███████▏ | 139/195 [00:12<00:03, 17.25it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 71%|███████▏ | 139/195 [00:12<00:03, 17.25it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 71%|███████▏ | 139/195 [00:13<00:03, 17.25it/s] 73%|███████▎ | 142/195 [00:13<00:02, 19.35it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 73%|███████▎ | 142/195 [00:13<00:02, 19.35it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 73%|███████▎ | 142/195 [00:13<00:02, 19.35it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.2.post_attention_layernorm.weight", shape: (3072,), dtype: float32 73%|███████▎ | 142/195 [00:13<00:02, 19.35it/s] 74%|███████▍ | 144/195 [00:13<00:02, 18.33it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 74%|███████▍ | 144/195 [00:13<00:02, 18.33it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 74%|███████▍ | 144/195 [00:13<00:02, 18.33it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 74%|███████▍ | 144/195 [00:13<00:02, 18.33it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 74%|███████▍ | 144/195 [00:13<00:02, 18.33it/s] 75%|███████▍ | 146/195 [00:13<00:02, 18.37it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.20.ln.weight", shape: (3072,), dtype: float32 75%|███████▍ | 146/195 [00:13<00:02, 18.37it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 75%|███████▍ | 146/195 [00:13<00:02, 18.37it/s] [2024-06-11 04:37:50] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 75%|███████▍ | 146/195 [00:13<00:02, 18.37it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 75%|███████▍ | 146/195 [00:13<00:02, 18.37it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 75%|███████▍ | 146/195 [00:13<00:02, 18.37it/s] 76%|███████▋ | 149/195 [00:13<00:02, 17.85it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.20.post_attention_layernorm.weight", shape: (3072,), dtype: float32 76%|███████▋ | 149/195 [00:13<00:02, 17.85it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 76%|███████▋ | 149/195 [00:13<00:02, 17.85it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 76%|███████▋ | 149/195 [00:13<00:02, 17.85it/s] 77%|███████▋ | 151/195 [00:13<00:02, 17.21it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 77%|███████▋ | 151/195 [00:13<00:02, 17.21it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 77%|███████▋ | 151/195 [00:13<00:02, 17.21it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 77%|███████▋ | 151/195 [00:13<00:02, 17.21it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 77%|███████▋ | 151/195 [00:13<00:02, 17.21it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.3.ln.weight", shape: (3072,), dtype: float32 77%|███████▋ | 151/195 [00:13<00:02, 17.21it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 77%|███████▋ | 151/195 [00:13<00:02, 17.21it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 77%|███████▋ | 151/195 [00:13<00:02, 17.21it/s] 79%|███████▉ | 155/195 [00:13<00:02, 19.31it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 79%|███████▉ | 155/195 [00:13<00:02, 19.31it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 79%|███████▉ | 155/195 [00:13<00:02, 19.31it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.3.post_attention_layernorm.weight", shape: (3072,), dtype: float32 79%|███████▉ | 155/195 [00:13<00:02, 19.31it/s] 81%|████████ | 157/195 [00:13<00:02, 18.54it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 81%|████████ | 157/195 [00:13<00:02, 18.54it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 81%|████████ | 157/195 [00:13<00:02, 18.54it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 81%|████████ | 157/195 [00:13<00:02, 18.54it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 81%|████████ | 157/195 [00:14<00:02, 18.54it/s] 82%|████████▏ | 159/195 [00:14<00:02, 17.95it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.4.ln.weight", shape: (3072,), dtype: float32 82%|████████▏ | 159/195 [00:14<00:02, 17.95it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 82%|████████▏ | 159/195 [00:14<00:02, 17.95it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 82%|████████▏ | 159/195 [00:14<00:02, 17.95it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 82%|████████▏ | 159/195 [00:14<00:02, 17.95it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 82%|████████▏ | 159/195 [00:14<00:02, 17.95it/s] 83%|████████▎ | 162/195 [00:14<00:01, 17.42it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.4.post_attention_layernorm.weight", shape: (3072,), dtype: float32 83%|████████▎ | 162/195 [00:14<00:01, 17.42it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 83%|████████▎ | 162/195 [00:14<00:01, 17.42it/s] [2024-06-11 04:37:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 83%|████████▎ | 162/195 [00:14<00:01, 17.42it/s] 84%|████████▍ | 164/195 [00:14<00:01, 16.81it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 84%|████████▍ | 164/195 [00:14<00:01, 16.81it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 84%|████████▍ | 164/195 [00:14<00:01, 16.81it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.5.ln.weight", shape: (3072,), dtype: float32 84%|████████▍ | 164/195 [00:14<00:01, 16.81it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 84%|████████▍ | 164/195 [00:14<00:01, 16.81it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 84%|████████▍ | 164/195 [00:14<00:01, 16.81it/s] 86%|████████▌ | 167/195 [00:14<00:01, 18.74it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 86%|████████▌ | 167/195 [00:14<00:01, 18.74it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 86%|████████▌ | 167/195 [00:14<00:01, 18.74it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.5.post_attention_layernorm.weight", shape: (3072,), dtype: float32 86%|████████▌ | 167/195 [00:14<00:01, 18.74it/s] 87%|████████▋ | 169/195 [00:14<00:01, 18.07it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 87%|████████▋ | 169/195 [00:14<00:01, 18.07it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 87%|████████▋ | 169/195 [00:14<00:01, 18.07it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 87%|████████▋ | 169/195 [00:14<00:01, 18.07it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 87%|████████▋ | 169/195 [00:14<00:01, 18.07it/s] 88%|████████▊ | 171/195 [00:14<00:01, 17.58it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.6.ln.weight", shape: (3072,), dtype: float32 88%|████████▊ | 171/195 [00:14<00:01, 17.58it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 88%|████████▊ | 171/195 [00:14<00:01, 17.58it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 88%|████████▊ | 171/195 [00:14<00:01, 17.58it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 88%|████████▊ | 171/195 [00:14<00:01, 17.58it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 88%|████████▊ | 171/195 [00:14<00:01, 17.58it/s] 89%|████████▉ | 174/195 [00:14<00:01, 18.19it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.6.post_attention_layernorm.weight", shape: (3072,), dtype: float32 89%|████████▉ | 174/195 [00:14<00:01, 18.19it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 89%|████████▉ | 174/195 [00:14<00:01, 18.19it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 89%|████████▉ | 174/195 [00:14<00:01, 18.19it/s] 90%|█████████ | 176/195 [00:14<00:01, 17.52it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 90%|█████████ | 176/195 [00:15<00:01, 17.52it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 90%|█████████ | 176/195 [00:15<00:01, 17.52it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.7.ln.weight", shape: (3072,), dtype: float32 90%|█████████ | 176/195 [00:15<00:01, 17.52it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 90%|█████████ | 176/195 [00:15<00:01, 17.52it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 90%|█████████ | 176/195 [00:15<00:01, 17.52it/s] 92%|█████████▏| 179/195 [00:15<00:00, 19.40it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 92%|█████████▏| 179/195 [00:15<00:00, 19.40it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 92%|█████████▏| 179/195 [00:15<00:00, 19.40it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.7.post_attention_layernorm.weight", shape: (3072,), dtype: float32 92%|█████████▏| 179/195 [00:15<00:00, 19.40it/s] 93%|█████████▎| 181/195 [00:15<00:00, 18.40it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 93%|█████████▎| 181/195 [00:15<00:00, 18.40it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 93%|█████████▎| 181/195 [00:15<00:00, 18.40it/s] [2024-06-11 04:37:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 93%|█████████▎| 181/195 [00:15<00:00, 18.40it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 93%|█████████▎| 181/195 [00:15<00:00, 18.40it/s] 94%|█████████▍| 183/195 [00:15<00:00, 17.82it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.8.ln.weight", shape: (3072,), dtype: float32 94%|█████████▍| 183/195 [00:15<00:00, 17.82it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 94%|█████████▍| 183/195 [00:15<00:00, 17.82it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 94%|█████████▍| 183/195 [00:15<00:00, 17.82it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 94%|█████████▍| 183/195 [00:15<00:00, 17.82it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 94%|█████████▍| 183/195 [00:15<00:00, 17.82it/s] 95%|█████████▌| 186/195 [00:15<00:00, 18.38it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.8.post_attention_layernorm.weight", shape: (3072,), dtype: float32 95%|█████████▌| 186/195 [00:15<00:00, 18.38it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 95%|█████████▌| 186/195 [00:15<00:00, 18.38it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 95%|█████████▌| 186/195 [00:15<00:00, 18.38it/s] 96%|█████████▋| 188/195 [00:15<00:00, 17.65it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 96%|█████████▋| 188/195 [00:15<00:00, 17.65it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 96%|█████████▋| 188/195 [00:15<00:00, 17.65it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.9.ln.weight", shape: (3072,), dtype: float32 96%|█████████▋| 188/195 [00:15<00:00, 17.65it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 96%|█████████▋| 188/195 [00:15<00:00, 17.65it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 96%|█████████▋| 188/195 [00:15<00:00, 17.65it/s] 98%|█████████▊| 191/195 [00:15<00:00, 19.65it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 98%|█████████▊| 191/195 [00:15<00:00, 19.65it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 98%|█████████▊| 191/195 [00:15<00:00, 19.65it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.9.post_attention_layernorm.weight", shape: (3072,), dtype: float32 98%|█████████▊| 191/195 [00:15<00:00, 19.65it/s] 99%|█████████▉| 193/195 [00:15<00:00, 18.69it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 99%|█████████▉| 193/195 [00:15<00:00, 18.69it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 99%|█████████▉| 193/195 [00:15<00:00, 18.69it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 99%|█████████▉| 193/195 [00:15<00:00, 18.69it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 99%|█████████▉| 193/195 [00:16<00:00, 18.69it/s] 100%|██████████| 195/195 [00:16<00:00, 17.99it/s] 100%|██████████| 195/195 [00:16<00:00, 12.18it/s] [2024-06-11 04:37:53] INFO huggingface_loader.py:197: Unloading HF weight file: /ssd2/models/Phi-3-mini-128k-instruct/model-00001-of-00002.safetensors [2024-06-11 04:37:54] INFO stats.py:77: Time usage: HF loading: 2.549 sec; Pre-quantization mapping: 1.873 sec; Quantization: 2.368 sec [2024-06-11 04:37:54] INFO stats.py:91: RAM usage: Peak RAM: 9.262 GB. Total bytes loaded from disk: 14.235 GB [2024-06-11 04:37:54] INFO convert_weight.py:155: Parameter size after quantization: 2.225 GB [2024-06-11 04:37:54] INFO convert_weight.py:160: Total parameters: 3,821,079,552 [2024-06-11 04:37:54] INFO convert_weight.py:161: Bits per parameter: 5.001 [2024-06-11 04:37:54] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC All finished, 83 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/ndarray-cache.json Also saved a bf16 record to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/ndarray-cache-b16.json /home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm gen_config /ssd2/models/Phi-3-mini-128k-instruct --quantization q4f32_1 --conv-template phi-3 --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC [2024-06-11 04:46:16] INFO auto_config.py:116: Found model configuration: /ssd2/models/Phi-3-mini-128k-instruct/config.json [2024-06-11 04:46:16] INFO auto_config.py:154: Found model type: phi3. Use `--model-type` to override. [2024-06-11 04:46:16] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072) [2024-06-11 04:46:16] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048 [2024-06-11 04:46:16] INFO config.py:107: Overriding max_batch_size from 1 to 80 [2024-06-11 04:46:16] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 1 [2024-06-11 04:46:16] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [32000, 32001, 32007] [2024-06-11 04:46:16] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 32000 [2024-06-11 04:46:16] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/tokenizer.model. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer.model [2024-06-11 04:46:16] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer.json [2024-06-11 04:46:16] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/vocab.json [2024-06-11 04:46:16] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/merges.txt [2024-06-11 04:46:16] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/added_tokens.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/added_tokens.json [2024-06-11 04:46:16] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer_config.json [2024-06-11 04:46:16] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_fallback', 'prepend_space_in_encode': True, 'strip_space_in_decode': True} [2024-06-11 04:46:16] INFO gen_config.py:32: [System default] Setting temperature: 1.0 [2024-06-11 04:46:16] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0 [2024-06-11 04:46:16] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0 [2024-06-11 04:46:16] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0 [2024-06-11 04:46:16] INFO gen_config.py:32: [System default] Setting top_p: 1.0 [2024-06-11 04:46:16] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/mlc-chat-config.json /home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm convert_weight /ssd2/models/Phi-3-mini-128k-instruct --quantization q4f32_1 --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC [2024-06-11 04:46:18] INFO auto_config.py:116: Found model configuration: /ssd2/models/Phi-3-mini-128k-instruct/config.json [2024-06-11 04:46:19] INFO auto_device.py:79: Found device: cuda:0 [2024-06-11 04:46:19] INFO auto_device.py:79: Found device: cuda:1 [2024-06-11 04:46:20] INFO auto_device.py:88: Not found device: rocm:0 [2024-06-11 04:46:21] INFO auto_device.py:88: Not found device: metal:0 [2024-06-11 04:46:22] INFO auto_device.py:79: Found device: vulkan:0 [2024-06-11 04:46:22] INFO auto_device.py:79: Found device: vulkan:1 [2024-06-11 04:46:22] INFO auto_device.py:79: Found device: vulkan:2 [2024-06-11 04:46:23] INFO auto_device.py:88: Not found device: opencl:0 [2024-06-11 04:46:23] INFO auto_device.py:35: Using device: cuda:0 [2024-06-11 04:46:23] INFO auto_weight.py:71: Finding weights in: /ssd2/models/Phi-3-mini-128k-instruct [2024-06-11 04:46:23] INFO auto_weight.py:137: Not found Huggingface PyTorch [2024-06-11 04:46:23] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /ssd2/models/Phi-3-mini-128k-instruct/model.safetensors.index.json [2024-06-11 04:46:23] INFO auto_weight.py:107: Using source weight configuration: /ssd2/models/Phi-3-mini-128k-instruct/model.safetensors.index.json. Use `--source` to override. [2024-06-11 04:46:23] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override. [2024-06-11 04:46:23] INFO auto_config.py:154: Found model type: phi3. Use `--model-type` to override. [2024-06-11 04:46:23] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072) [2024-06-11 04:46:23] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048 Weight conversion with arguments: --config /ssd2/models/Phi-3-mini-128k-instruct/config.json --quantization GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7) --model-type phi3 --device cuda:0 --source /ssd2/models/Phi-3-mini-128k-instruct/model.safetensors.index.json --source-format huggingface-safetensor --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC Start storing to cache /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC 0%| | 0/195 [00:00 type is zero. setattr(self, word, getattr(machar, word).flat[0]) /home/rickzhou/miniconda3/envs/mlc/lib/python3.11/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) 1%| | 1/195 [00:02<09:14, 2.86s/it] [2024-06-11 04:46:29] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.21.ln.weight", shape: (3072,), dtype: float32 1%| | 1/195 [00:02<09:14, 2.86s/it] [2024-06-11 04:46:29] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 8192), float32, cuda, axis=1, output_transpose=False) 1%| | 1/195 [00:02<09:14, 2.86s/it] [2024-06-11 04:46:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 1%| | 1/195 [00:03<09:14, 2.86s/it] [2024-06-11 04:46:29] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 1%| | 1/195 [00:03<09:14, 2.86s/it] 2%|▏ | 3/195 [00:03<02:45, 1.16it/s] [2024-06-11 04:46:29] INFO group_quantization.py:217: Compiling quantize function for key: ((16384, 3072), float32, cuda, axis=1, output_transpose=False) 2%|▏ | 3/195 [00:03<02:45, 1.16it/s] [2024-06-11 04:46:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 2%|▏ | 3/195 [00:03<02:45, 1.16it/s] [2024-06-11 04:46:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 2%|▏ | 3/195 [00:03<02:45, 1.16it/s] 2%|▏ | 4/195 [00:03<02:18, 1.38it/s] [2024-06-11 04:46:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.21.post_attention_layernorm.weight", shape: (3072,), dtype: float32 2%|▏ | 4/195 [00:03<02:18, 1.38it/s] [2024-06-11 04:46:30] INFO group_quantization.py:217: Compiling quantize function for key: ((9216, 3072), float32, cuda, axis=1, output_transpose=False) 2%|▏ | 4/195 [00:03<02:18, 1.38it/s] [2024-06-11 04:46:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 2%|▏ | 4/195 [00:03<02:18, 1.38it/s] [2024-06-11 04:46:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 2%|▏ | 4/195 [00:04<02:18, 1.38it/s] 3%|▎ | 6/195 [00:04<01:28, 2.13it/s] [2024-06-11 04:46:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.22.ln.weight", shape: (3072,), dtype: float32 3%|▎ | 6/195 [00:04<01:28, 2.13it/s] [2024-06-11 04:46:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 3%|▎ | 6/195 [00:04<01:28, 2.13it/s] [2024-06-11 04:46:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 3%|▎ | 6/195 [00:04<01:28, 2.13it/s] [2024-06-11 04:46:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 3%|▎ | 6/195 [00:04<01:28, 2.13it/s] [2024-06-11 04:46:30] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 3%|▎ | 6/195 [00:04<01:28, 2.13it/s] 5%|▍ | 9/195 [00:04<00:48, 3.83it/s] [2024-06-11 04:46:30] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.22.post_attention_layernorm.weight", shape: (3072,), dtype: float32 5%|▍ | 9/195 [00:04<00:48, 3.83it/s] [2024-06-11 04:46:30] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 3072), float32, cuda, axis=1, output_transpose=False) 5%|▍ | 9/195 [00:04<00:48, 3.83it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 5%|▍ | 9/195 [00:04<00:48, 3.83it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 5%|▍ | 9/195 [00:04<00:48, 3.83it/s] 6%|▌ | 11/195 [00:04<00:45, 4.02it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 6%|▌ | 11/195 [00:04<00:45, 4.02it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 6%|▌ | 11/195 [00:04<00:45, 4.02it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.23.ln.weight", shape: (3072,), dtype: float32 6%|▌ | 11/195 [00:04<00:45, 4.02it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 6%|▌ | 11/195 [00:04<00:45, 4.02it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 6%|▌ | 11/195 [00:04<00:45, 4.02it/s] 7%|▋ | 14/195 [00:04<00:30, 6.01it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 7%|▋ | 14/195 [00:04<00:30, 6.01it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 7%|▋ | 14/195 [00:05<00:30, 6.01it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.23.post_attention_layernorm.weight", shape: (3072,), dtype: float32 7%|▋ | 14/195 [00:05<00:30, 6.01it/s] 8%|▊ | 16/195 [00:05<00:25, 7.13it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 8%|▊ | 16/195 [00:05<00:25, 7.13it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 8%|▊ | 16/195 [00:05<00:25, 7.13it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 8%|▊ | 16/195 [00:05<00:25, 7.13it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 8%|▊ | 16/195 [00:05<00:25, 7.13it/s] 9%|▉ | 18/195 [00:05<00:21, 8.38it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.24.ln.weight", shape: (3072,), dtype: float32 9%|▉ | 18/195 [00:05<00:21, 8.38it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 9%|▉ | 18/195 [00:05<00:21, 8.38it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 9%|▉ | 18/195 [00:05<00:21, 8.38it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 9%|▉ | 18/195 [00:05<00:21, 8.38it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 9%|▉ | 18/195 [00:05<00:21, 8.38it/s] 11%|█ | 21/195 [00:05<00:16, 10.49it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.24.post_attention_layernorm.weight", shape: (3072,), dtype: float32 11%|█ | 21/195 [00:05<00:16, 10.49it/s] [2024-06-11 04:46:31] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 11%|█ | 21/195 [00:05<00:16, 10.49it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 11%|█ | 21/195 [00:05<00:16, 10.49it/s] 12%|█▏ | 23/195 [00:05<00:14, 11.52it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 12%|█▏ | 23/195 [00:05<00:14, 11.52it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 12%|█▏ | 23/195 [00:05<00:14, 11.52it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.25.ln.weight", shape: (3072,), dtype: float32 12%|█▏ | 23/195 [00:05<00:14, 11.52it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 12%|█▏ | 23/195 [00:05<00:14, 11.52it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 12%|█▏ | 23/195 [00:05<00:14, 11.52it/s] 13%|█▎ | 26/195 [00:05<00:11, 14.12it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 13%|█▎ | 26/195 [00:05<00:11, 14.12it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 13%|█▎ | 26/195 [00:05<00:11, 14.12it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.25.post_attention_layernorm.weight", shape: (3072,), dtype: float32 13%|█▎ | 26/195 [00:05<00:11, 14.12it/s] 14%|█▍ | 28/195 [00:05<00:11, 14.24it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 14%|█▍ | 28/195 [00:05<00:11, 14.24it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 14%|█▍ | 28/195 [00:05<00:11, 14.24it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 14%|█▍ | 28/195 [00:05<00:11, 14.24it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 14%|█▍ | 28/195 [00:05<00:11, 14.24it/s] 15%|█▌ | 30/195 [00:05<00:10, 15.02it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.26.ln.weight", shape: (3072,), dtype: float32 15%|█▌ | 30/195 [00:05<00:10, 15.02it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 15%|█▌ | 30/195 [00:05<00:10, 15.02it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 15%|█▌ | 30/195 [00:05<00:10, 15.02it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 15%|█▌ | 30/195 [00:05<00:10, 15.02it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 15%|█▌ | 30/195 [00:05<00:10, 15.02it/s] 17%|█▋ | 33/195 [00:05<00:10, 16.16it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.26.post_attention_layernorm.weight", shape: (3072,), dtype: float32 17%|█▋ | 33/195 [00:05<00:10, 16.16it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 17%|█▋ | 33/195 [00:05<00:10, 16.16it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 17%|█▋ | 33/195 [00:06<00:10, 16.16it/s] 18%|█▊ | 35/195 [00:06<00:10, 15.99it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 18%|█▊ | 35/195 [00:06<00:10, 15.99it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 18%|█▊ | 35/195 [00:06<00:10, 15.99it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.27.ln.weight", shape: (3072,), dtype: float32 18%|█▊ | 35/195 [00:06<00:10, 15.99it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 18%|█▊ | 35/195 [00:06<00:10, 15.99it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 18%|█▊ | 35/195 [00:06<00:10, 15.99it/s] 19%|█▉ | 38/195 [00:06<00:08, 18.13it/s] [2024-06-11 04:46:32] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 19%|█▉ | 38/195 [00:06<00:08, 18.13it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 19%|█▉ | 38/195 [00:06<00:08, 18.13it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.27.post_attention_layernorm.weight", shape: (3072,), dtype: float32 19%|█▉ | 38/195 [00:06<00:08, 18.13it/s] 21%|██ | 40/195 [00:06<00:09, 16.99it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 21%|██ | 40/195 [00:06<00:09, 16.99it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 21%|██ | 40/195 [00:06<00:09, 16.99it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 21%|██ | 40/195 [00:06<00:09, 16.99it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 21%|██ | 40/195 [00:06<00:09, 16.99it/s] 22%|██▏ | 42/195 [00:06<00:09, 16.87it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.28.ln.weight", shape: (3072,), dtype: float32 22%|██▏ | 42/195 [00:06<00:09, 16.87it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 22%|██▏ | 42/195 [00:06<00:09, 16.87it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 22%|██▏ | 42/195 [00:06<00:09, 16.87it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 22%|██▏ | 42/195 [00:06<00:09, 16.87it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 22%|██▏ | 42/195 [00:06<00:09, 16.87it/s] 23%|██▎ | 45/195 [00:06<00:08, 17.46it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.28.post_attention_layernorm.weight", shape: (3072,), dtype: float32 23%|██▎ | 45/195 [00:06<00:08, 17.46it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 23%|██▎ | 45/195 [00:06<00:08, 17.46it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 23%|██▎ | 45/195 [00:06<00:08, 17.46it/s] 24%|██▍ | 47/195 [00:06<00:08, 16.91it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 24%|██▍ | 47/195 [00:06<00:08, 16.91it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 24%|██▍ | 47/195 [00:06<00:08, 16.91it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.29.ln.weight", shape: (3072,), dtype: float32 24%|██▍ | 47/195 [00:06<00:08, 16.91it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 24%|██▍ | 47/195 [00:06<00:08, 16.91it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 24%|██▍ | 47/195 [00:06<00:08, 16.91it/s] 26%|██▌ | 50/195 [00:06<00:07, 18.79it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 26%|██▌ | 50/195 [00:06<00:07, 18.79it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 26%|██▌ | 50/195 [00:07<00:07, 18.79it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.29.post_attention_layernorm.weight", shape: (3072,), dtype: float32 26%|██▌ | 50/195 [00:07<00:07, 18.79it/s] 27%|██▋ | 52/195 [00:07<00:08, 17.52it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 27%|██▋ | 52/195 [00:07<00:08, 17.52it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 27%|██▋ | 52/195 [00:07<00:08, 17.52it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 27%|██▋ | 52/195 [00:07<00:08, 17.52it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 27%|██▋ | 52/195 [00:07<00:08, 17.52it/s] 28%|██▊ | 54/195 [00:07<00:08, 17.49it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.30.ln.weight", shape: (3072,), dtype: float32 28%|██▊ | 54/195 [00:07<00:08, 17.49it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 28%|██▊ | 54/195 [00:07<00:08, 17.49it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 28%|██▊ | 54/195 [00:07<00:08, 17.49it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 28%|██▊ | 54/195 [00:07<00:08, 17.49it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 28%|██▊ | 54/195 [00:07<00:08, 17.49it/s] 29%|██▉ | 57/195 [00:07<00:07, 17.92it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.30.post_attention_layernorm.weight", shape: (3072,), dtype: float32 29%|██▉ | 57/195 [00:07<00:07, 17.92it/s] [2024-06-11 04:46:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 29%|██▉ | 57/195 [00:07<00:07, 17.92it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 29%|██▉ | 57/195 [00:07<00:07, 17.92it/s] 30%|███ | 59/195 [00:07<00:07, 17.24it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 30%|███ | 59/195 [00:07<00:07, 17.24it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 30%|███ | 59/195 [00:07<00:07, 17.24it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.31.ln.weight", shape: (3072,), dtype: float32 30%|███ | 59/195 [00:07<00:07, 17.24it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 30%|███ | 59/195 [00:07<00:07, 17.24it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 30%|███ | 59/195 [00:07<00:07, 17.24it/s] 32%|███▏ | 62/195 [00:07<00:06, 19.23it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 32%|███▏ | 62/195 [00:07<00:06, 19.23it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 32%|███▏ | 62/195 [00:07<00:06, 19.23it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.31.post_attention_layernorm.weight", shape: (3072,), dtype: float32 32%|███▏ | 62/195 [00:07<00:06, 19.23it/s] 33%|███▎ | 64/195 [00:07<00:07, 17.82it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 33%|███▎ | 64/195 [00:07<00:07, 17.82it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 33%|███▎ | 64/195 [00:07<00:07, 17.82it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 33%|███▎ | 64/195 [00:07<00:07, 17.82it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 33%|███▎ | 64/195 [00:07<00:07, 17.82it/s] 34%|███▍ | 66/195 [00:07<00:07, 17.74it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.norm.weight", shape: (3072,), dtype: float32 34%|███▍ | 66/195 [00:07<00:07, 17.74it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:197: Unloading HF weight file: /ssd2/models/Phi-3-mini-128k-instruct/model-00002-of-00002.safetensors 34%|███▍ | 66/195 [00:07<00:07, 17.74it/s] [2024-06-11 04:46:34] INFO huggingface_loader.py:185: Loading HF parameters from: /ssd2/models/Phi-3-mini-128k-instruct/model-00001-of-00002.safetensors 34%|███▍ | 66/195 [00:08<00:07, 17.74it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.embd.q_weight", shape: (32064, 384), dtype: uint32 34%|███▍ | 66/195 [00:08<00:07, 17.74it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.embd.q_scale", shape: (32064, 96), dtype: float32 34%|███▍ | 66/195 [00:08<00:07, 17.74it/s] 35%|███▍ | 68/195 [00:08<00:24, 5.15it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.0.ln.weight", shape: (3072,), dtype: float32 35%|███▍ | 68/195 [00:08<00:24, 5.15it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 35%|███▍ | 68/195 [00:08<00:24, 5.15it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 35%|███▍ | 68/195 [00:09<00:24, 5.15it/s] 36%|███▌ | 70/195 [00:09<00:19, 6.48it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 36%|███▌ | 70/195 [00:09<00:19, 6.48it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 36%|███▌ | 70/195 [00:09<00:19, 6.48it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.0.post_attention_layernorm.weight", shape: (3072,), dtype: float32 36%|███▌ | 70/195 [00:09<00:19, 6.48it/s] 37%|███▋ | 72/195 [00:09<00:15, 7.69it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 37%|███▋ | 72/195 [00:09<00:15, 7.69it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 37%|███▋ | 72/195 [00:09<00:15, 7.69it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 37%|███▋ | 72/195 [00:09<00:15, 7.69it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 37%|███▋ | 72/195 [00:09<00:15, 7.69it/s] 38%|███▊ | 74/195 [00:09<00:13, 9.13it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.1.ln.weight", shape: (3072,), dtype: float32 38%|███▊ | 74/195 [00:09<00:13, 9.13it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 38%|███▊ | 74/195 [00:09<00:13, 9.13it/s] [2024-06-11 04:46:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 38%|███▊ | 74/195 [00:09<00:13, 9.13it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 38%|███▊ | 74/195 [00:09<00:13, 9.13it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 38%|███▊ | 74/195 [00:09<00:13, 9.13it/s] 39%|███▉ | 77/195 [00:09<00:10, 11.33it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.1.post_attention_layernorm.weight", shape: (3072,), dtype: float32 39%|███▉ | 77/195 [00:09<00:10, 11.33it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 39%|███▉ | 77/195 [00:09<00:10, 11.33it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 39%|███▉ | 77/195 [00:09<00:10, 11.33it/s] 41%|████ | 79/195 [00:09<00:09, 12.21it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 41%|████ | 79/195 [00:09<00:09, 12.21it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 41%|████ | 79/195 [00:09<00:09, 12.21it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.10.ln.weight", shape: (3072,), dtype: float32 41%|████ | 79/195 [00:09<00:09, 12.21it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 41%|████ | 79/195 [00:09<00:09, 12.21it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 41%|████ | 79/195 [00:09<00:09, 12.21it/s] 42%|████▏ | 82/195 [00:09<00:07, 14.75it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 42%|████▏ | 82/195 [00:09<00:07, 14.75it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 42%|████▏ | 82/195 [00:09<00:07, 14.75it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.10.post_attention_layernorm.weight", shape: (3072,), dtype: float32 42%|████▏ | 82/195 [00:09<00:07, 14.75it/s] 43%|████▎ | 84/195 [00:09<00:07, 14.27it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 43%|████▎ | 84/195 [00:09<00:07, 14.27it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 43%|████▎ | 84/195 [00:09<00:07, 14.27it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 43%|████▎ | 84/195 [00:09<00:07, 14.27it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 43%|████▎ | 84/195 [00:10<00:07, 14.27it/s] 44%|████▍ | 86/195 [00:10<00:07, 14.87it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.11.ln.weight", shape: (3072,), dtype: float32 44%|████▍ | 86/195 [00:10<00:07, 14.87it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 44%|████▍ | 86/195 [00:10<00:07, 14.87it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 44%|████▍ | 86/195 [00:10<00:07, 14.87it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 44%|████▍ | 86/195 [00:10<00:07, 14.87it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 44%|████▍ | 86/195 [00:10<00:07, 14.87it/s] 46%|████▌ | 89/195 [00:10<00:06, 15.98it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.11.post_attention_layernorm.weight", shape: (3072,), dtype: float32 46%|████▌ | 89/195 [00:10<00:06, 15.98it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 46%|████▌ | 89/195 [00:10<00:06, 15.98it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 46%|████▌ | 89/195 [00:10<00:06, 15.98it/s] 47%|████▋ | 91/195 [00:10<00:06, 15.78it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 47%|████▋ | 91/195 [00:10<00:06, 15.78it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 47%|████▋ | 91/195 [00:10<00:06, 15.78it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.12.ln.weight", shape: (3072,), dtype: float32 47%|████▋ | 91/195 [00:10<00:06, 15.78it/s] [2024-06-11 04:46:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 47%|████▋ | 91/195 [00:10<00:06, 15.78it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 47%|████▋ | 91/195 [00:10<00:06, 15.78it/s] 48%|████▊ | 94/195 [00:10<00:05, 17.62it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 48%|████▊ | 94/195 [00:10<00:05, 17.62it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 48%|████▊ | 94/195 [00:10<00:05, 17.62it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.12.post_attention_layernorm.weight", shape: (3072,), dtype: float32 48%|████▊ | 94/195 [00:10<00:05, 17.62it/s] 49%|████▉ | 96/195 [00:10<00:05, 16.52it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 49%|████▉ | 96/195 [00:10<00:05, 16.52it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 49%|████▉ | 96/195 [00:10<00:05, 16.52it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 49%|████▉ | 96/195 [00:10<00:05, 16.52it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 49%|████▉ | 96/195 [00:10<00:05, 16.52it/s] 50%|█████ | 98/195 [00:10<00:05, 16.60it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.13.ln.weight", shape: (3072,), dtype: float32 50%|█████ | 98/195 [00:10<00:05, 16.60it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 50%|█████ | 98/195 [00:10<00:05, 16.60it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 50%|█████ | 98/195 [00:10<00:05, 16.60it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 50%|█████ | 98/195 [00:10<00:05, 16.60it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 50%|█████ | 98/195 [00:10<00:05, 16.60it/s] 52%|█████▏ | 101/195 [00:10<00:05, 17.21it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.13.post_attention_layernorm.weight", shape: (3072,), dtype: float32 52%|█████▏ | 101/195 [00:10<00:05, 17.21it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 52%|█████▏ | 101/195 [00:10<00:05, 17.21it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 52%|█████▏ | 101/195 [00:10<00:05, 17.21it/s] 53%|█████▎ | 103/195 [00:10<00:05, 16.63it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 53%|█████▎ | 103/195 [00:11<00:05, 16.63it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 53%|█████▎ | 103/195 [00:11<00:05, 16.63it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.14.ln.weight", shape: (3072,), dtype: float32 53%|█████▎ | 103/195 [00:11<00:05, 16.63it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 53%|█████▎ | 103/195 [00:11<00:05, 16.63it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 53%|█████▎ | 103/195 [00:11<00:05, 16.63it/s] 54%|█████▍ | 106/195 [00:11<00:04, 18.34it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 54%|█████▍ | 106/195 [00:11<00:04, 18.34it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 54%|█████▍ | 106/195 [00:11<00:04, 18.34it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.14.post_attention_layernorm.weight", shape: (3072,), dtype: float32 54%|█████▍ | 106/195 [00:11<00:04, 18.34it/s] 55%|█████▌ | 108/195 [00:11<00:05, 17.05it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 55%|█████▌ | 108/195 [00:11<00:05, 17.05it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 55%|█████▌ | 108/195 [00:11<00:05, 17.05it/s] [2024-06-11 04:46:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 55%|█████▌ | 108/195 [00:11<00:05, 17.05it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 55%|█████▌ | 108/195 [00:11<00:05, 17.05it/s] 56%|█████▋ | 110/195 [00:11<00:05, 16.95it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.15.ln.weight", shape: (3072,), dtype: float32 56%|█████▋ | 110/195 [00:11<00:05, 16.95it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 56%|█████▋ | 110/195 [00:11<00:05, 16.95it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 56%|█████▋ | 110/195 [00:11<00:05, 16.95it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 56%|█████▋ | 110/195 [00:11<00:05, 16.95it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 56%|█████▋ | 110/195 [00:11<00:05, 16.95it/s] 58%|█████▊ | 113/195 [00:11<00:04, 17.63it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.15.post_attention_layernorm.weight", shape: (3072,), dtype: float32 58%|█████▊ | 113/195 [00:11<00:04, 17.63it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 58%|█████▊ | 113/195 [00:11<00:04, 17.63it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 58%|█████▊ | 113/195 [00:11<00:04, 17.63it/s] 59%|█████▉ | 115/195 [00:11<00:04, 16.97it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 59%|█████▉ | 115/195 [00:11<00:04, 16.97it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 59%|█████▉ | 115/195 [00:11<00:04, 16.97it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.16.ln.weight", shape: (3072,), dtype: float32 59%|█████▉ | 115/195 [00:11<00:04, 16.97it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 59%|█████▉ | 115/195 [00:11<00:04, 16.97it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 59%|█████▉ | 115/195 [00:11<00:04, 16.97it/s] 61%|██████ | 118/195 [00:11<00:04, 18.59it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 61%|██████ | 118/195 [00:11<00:04, 18.59it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 61%|██████ | 118/195 [00:11<00:04, 18.59it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.16.post_attention_layernorm.weight", shape: (3072,), dtype: float32 61%|██████ | 118/195 [00:11<00:04, 18.59it/s] 62%|██████▏ | 120/195 [00:11<00:04, 17.29it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 62%|██████▏ | 120/195 [00:11<00:04, 17.29it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 62%|██████▏ | 120/195 [00:11<00:04, 17.29it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 62%|██████▏ | 120/195 [00:11<00:04, 17.29it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 62%|██████▏ | 120/195 [00:12<00:04, 17.29it/s] 63%|██████▎ | 122/195 [00:12<00:04, 17.17it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.17.ln.weight", shape: (3072,), dtype: float32 63%|██████▎ | 122/195 [00:12<00:04, 17.17it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 63%|██████▎ | 122/195 [00:12<00:04, 17.17it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 63%|██████▎ | 122/195 [00:12<00:04, 17.17it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 63%|██████▎ | 122/195 [00:12<00:04, 17.17it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 63%|██████▎ | 122/195 [00:12<00:04, 17.17it/s] 64%|██████▍ | 125/195 [00:12<00:03, 17.64it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.17.post_attention_layernorm.weight", shape: (3072,), dtype: float32 64%|██████▍ | 125/195 [00:12<00:03, 17.64it/s] [2024-06-11 04:46:38] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 64%|██████▍ | 125/195 [00:12<00:03, 17.64it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 64%|██████▍ | 125/195 [00:12<00:03, 17.64it/s] 65%|██████▌ | 127/195 [00:12<00:03, 17.03it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 65%|██████▌ | 127/195 [00:12<00:03, 17.03it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 65%|██████▌ | 127/195 [00:12<00:03, 17.03it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.18.ln.weight", shape: (3072,), dtype: float32 65%|██████▌ | 127/195 [00:12<00:03, 17.03it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 65%|██████▌ | 127/195 [00:12<00:03, 17.03it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 65%|██████▌ | 127/195 [00:12<00:03, 17.03it/s] 67%|██████▋ | 130/195 [00:12<00:03, 18.76it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 67%|██████▋ | 130/195 [00:12<00:03, 18.76it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 67%|██████▋ | 130/195 [00:12<00:03, 18.76it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.18.post_attention_layernorm.weight", shape: (3072,), dtype: float32 67%|██████▋ | 130/195 [00:12<00:03, 18.76it/s] 68%|██████▊ | 132/195 [00:12<00:03, 17.30it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 68%|██████▊ | 132/195 [00:12<00:03, 17.30it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 68%|██████▊ | 132/195 [00:12<00:03, 17.30it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 68%|██████▊ | 132/195 [00:12<00:03, 17.30it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 68%|██████▊ | 132/195 [00:12<00:03, 17.30it/s] 69%|██████▊ | 134/195 [00:12<00:03, 17.22it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.19.ln.weight", shape: (3072,), dtype: float32 69%|██████▊ | 134/195 [00:12<00:03, 17.22it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 69%|██████▊ | 134/195 [00:12<00:03, 17.22it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 69%|██████▊ | 134/195 [00:12<00:03, 17.22it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 69%|██████▊ | 134/195 [00:12<00:03, 17.22it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 69%|██████▊ | 134/195 [00:12<00:03, 17.22it/s] 70%|███████ | 137/195 [00:12<00:03, 17.65it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.19.post_attention_layernorm.weight", shape: (3072,), dtype: float32 70%|███████ | 137/195 [00:12<00:03, 17.65it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 70%|███████ | 137/195 [00:12<00:03, 17.65it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 70%|███████ | 137/195 [00:13<00:03, 17.65it/s] 71%|███████▏ | 139/195 [00:13<00:03, 16.93it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 71%|███████▏ | 139/195 [00:13<00:03, 16.93it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 71%|███████▏ | 139/195 [00:13<00:03, 16.93it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.2.ln.weight", shape: (3072,), dtype: float32 71%|███████▏ | 139/195 [00:13<00:03, 16.93it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 71%|███████▏ | 139/195 [00:13<00:03, 16.93it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 71%|███████▏ | 139/195 [00:13<00:03, 16.93it/s] 73%|███████▎ | 142/195 [00:13<00:02, 18.57it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 73%|███████▎ | 142/195 [00:13<00:02, 18.57it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 73%|███████▎ | 142/195 [00:13<00:02, 18.57it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.2.post_attention_layernorm.weight", shape: (3072,), dtype: float32 73%|███████▎ | 142/195 [00:13<00:02, 18.57it/s] 74%|███████▍ | 144/195 [00:13<00:02, 17.18it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 74%|███████▍ | 144/195 [00:13<00:02, 17.18it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 74%|███████▍ | 144/195 [00:13<00:02, 17.18it/s] [2024-06-11 04:46:39] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 74%|███████▍ | 144/195 [00:13<00:02, 17.18it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 74%|███████▍ | 144/195 [00:13<00:02, 17.18it/s] 75%|███████▍ | 146/195 [00:13<00:02, 17.12it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.20.ln.weight", shape: (3072,), dtype: float32 75%|███████▍ | 146/195 [00:13<00:02, 17.12it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 75%|███████▍ | 146/195 [00:13<00:02, 17.12it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 75%|███████▍ | 146/195 [00:13<00:02, 17.12it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 75%|███████▍ | 146/195 [00:13<00:02, 17.12it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 75%|███████▍ | 146/195 [00:13<00:02, 17.12it/s] 76%|███████▋ | 149/195 [00:13<00:02, 17.54it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.20.post_attention_layernorm.weight", shape: (3072,), dtype: float32 76%|███████▋ | 149/195 [00:13<00:02, 17.54it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 76%|███████▋ | 149/195 [00:13<00:02, 17.54it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 76%|███████▋ | 149/195 [00:13<00:02, 17.54it/s] 77%|███████▋ | 151/195 [00:13<00:02, 16.87it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 77%|███████▋ | 151/195 [00:13<00:02, 16.87it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 77%|███████▋ | 151/195 [00:13<00:02, 16.87it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 77%|███████▋ | 151/195 [00:13<00:02, 16.87it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 77%|███████▋ | 151/195 [00:13<00:02, 16.87it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.3.ln.weight", shape: (3072,), dtype: float32 77%|███████▋ | 151/195 [00:13<00:02, 16.87it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 77%|███████▋ | 151/195 [00:13<00:02, 16.87it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 77%|███████▋ | 151/195 [00:13<00:02, 16.87it/s] 79%|███████▉ | 155/195 [00:13<00:02, 18.64it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 79%|███████▉ | 155/195 [00:13<00:02, 18.64it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 79%|███████▉ | 155/195 [00:14<00:02, 18.64it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.3.post_attention_layernorm.weight", shape: (3072,), dtype: float32 79%|███████▉ | 155/195 [00:14<00:02, 18.64it/s] 81%|████████ | 157/195 [00:14<00:02, 17.33it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 81%|████████ | 157/195 [00:14<00:02, 17.33it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 81%|████████ | 157/195 [00:14<00:02, 17.33it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 81%|████████ | 157/195 [00:14<00:02, 17.33it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 81%|████████ | 157/195 [00:14<00:02, 17.33it/s] 82%|████████▏ | 159/195 [00:14<00:02, 17.23it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.4.ln.weight", shape: (3072,), dtype: float32 82%|████████▏ | 159/195 [00:14<00:02, 17.23it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 82%|████████▏ | 159/195 [00:14<00:02, 17.23it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 82%|████████▏ | 159/195 [00:14<00:02, 17.23it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 82%|████████▏ | 159/195 [00:14<00:02, 17.23it/s] [2024-06-11 04:46:40] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 82%|████████▏ | 159/195 [00:14<00:02, 17.23it/s] 83%|████████▎ | 162/195 [00:14<00:01, 17.00it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.4.post_attention_layernorm.weight", shape: (3072,), dtype: float32 83%|████████▎ | 162/195 [00:14<00:01, 17.00it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 83%|████████▎ | 162/195 [00:14<00:01, 17.00it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 83%|████████▎ | 162/195 [00:14<00:01, 17.00it/s] 84%|████████▍ | 164/195 [00:14<00:01, 16.40it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 84%|████████▍ | 164/195 [00:14<00:01, 16.40it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 84%|████████▍ | 164/195 [00:14<00:01, 16.40it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.5.ln.weight", shape: (3072,), dtype: float32 84%|████████▍ | 164/195 [00:14<00:01, 16.40it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 84%|████████▍ | 164/195 [00:14<00:01, 16.40it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 84%|████████▍ | 164/195 [00:14<00:01, 16.40it/s] 86%|████████▌ | 167/195 [00:14<00:01, 18.13it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 86%|████████▌ | 167/195 [00:14<00:01, 18.13it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 86%|████████▌ | 167/195 [00:14<00:01, 18.13it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.5.post_attention_layernorm.weight", shape: (3072,), dtype: float32 86%|████████▌ | 167/195 [00:14<00:01, 18.13it/s] 87%|████████▋ | 169/195 [00:14<00:01, 16.94it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 87%|████████▋ | 169/195 [00:14<00:01, 16.94it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 87%|████████▋ | 169/195 [00:14<00:01, 16.94it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 87%|████████▋ | 169/195 [00:14<00:01, 16.94it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 87%|████████▋ | 169/195 [00:14<00:01, 16.94it/s] 88%|████████▊ | 171/195 [00:14<00:01, 16.93it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.6.ln.weight", shape: (3072,), dtype: float32 88%|████████▊ | 171/195 [00:14<00:01, 16.93it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 88%|████████▊ | 171/195 [00:14<00:01, 16.93it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 88%|████████▊ | 171/195 [00:14<00:01, 16.93it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 88%|████████▊ | 171/195 [00:14<00:01, 16.93it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 88%|████████▊ | 171/195 [00:15<00:01, 16.93it/s] 89%|████████▉ | 174/195 [00:15<00:01, 16.88it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.6.post_attention_layernorm.weight", shape: (3072,), dtype: float32 89%|████████▉ | 174/195 [00:15<00:01, 16.88it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 89%|████████▉ | 174/195 [00:15<00:01, 16.88it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 89%|████████▉ | 174/195 [00:15<00:01, 16.88it/s] 90%|█████████ | 176/195 [00:15<00:01, 16.10it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 90%|█████████ | 176/195 [00:15<00:01, 16.10it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 90%|█████████ | 176/195 [00:15<00:01, 16.10it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.7.ln.weight", shape: (3072,), dtype: float32 90%|█████████ | 176/195 [00:15<00:01, 16.10it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 90%|█████████ | 176/195 [00:15<00:01, 16.10it/s] [2024-06-11 04:46:41] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 90%|█████████ | 176/195 [00:15<00:01, 16.10it/s] 92%|█████████▏| 179/195 [00:15<00:00, 17.91it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 92%|█████████▏| 179/195 [00:15<00:00, 17.91it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 92%|█████████▏| 179/195 [00:15<00:00, 17.91it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.7.post_attention_layernorm.weight", shape: (3072,), dtype: float32 92%|█████████▏| 179/195 [00:15<00:00, 17.91it/s] 93%|█████████▎| 181/195 [00:15<00:00, 16.78it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 93%|█████████▎| 181/195 [00:15<00:00, 16.78it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 93%|█████████▎| 181/195 [00:15<00:00, 16.78it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 93%|█████████▎| 181/195 [00:15<00:00, 16.78it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 93%|█████████▎| 181/195 [00:15<00:00, 16.78it/s] 94%|█████████▍| 183/195 [00:15<00:00, 16.83it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.8.ln.weight", shape: (3072,), dtype: float32 94%|█████████▍| 183/195 [00:15<00:00, 16.83it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 94%|█████████▍| 183/195 [00:15<00:00, 16.83it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 94%|█████████▍| 183/195 [00:15<00:00, 16.83it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 94%|█████████▍| 183/195 [00:15<00:00, 16.83it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 94%|█████████▍| 183/195 [00:15<00:00, 16.83it/s] 95%|█████████▌| 186/195 [00:15<00:00, 17.43it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.8.post_attention_layernorm.weight", shape: (3072,), dtype: float32 95%|█████████▌| 186/195 [00:15<00:00, 17.43it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 95%|█████████▌| 186/195 [00:15<00:00, 17.43it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 95%|█████████▌| 186/195 [00:15<00:00, 17.43it/s] 96%|█████████▋| 188/195 [00:15<00:00, 16.83it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 96%|█████████▋| 188/195 [00:15<00:00, 16.83it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 96%|█████████▋| 188/195 [00:15<00:00, 16.83it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.9.ln.weight", shape: (3072,), dtype: float32 96%|█████████▋| 188/195 [00:15<00:00, 16.83it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 96%|█████████▋| 188/195 [00:15<00:00, 16.83it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 96%|█████████▋| 188/195 [00:16<00:00, 16.83it/s] 98%|█████████▊| 191/195 [00:16<00:00, 18.37it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 98%|█████████▊| 191/195 [00:16<00:00, 18.37it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 98%|█████████▊| 191/195 [00:16<00:00, 18.37it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.9.post_attention_layernorm.weight", shape: (3072,), dtype: float32 98%|█████████▊| 191/195 [00:16<00:00, 18.37it/s] 99%|█████████▉| 193/195 [00:16<00:00, 17.28it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 99%|█████████▉| 193/195 [00:16<00:00, 17.28it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 99%|█████████▉| 193/195 [00:16<00:00, 17.28it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 99%|█████████▉| 193/195 [00:16<00:00, 17.28it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 99%|█████████▉| 193/195 [00:16<00:00, 17.28it/s] 100%|██████████| 195/195 [00:16<00:00, 17.23it/s] 100%|██████████| 195/195 [00:16<00:00, 11.98it/s] [2024-06-11 04:46:42] INFO huggingface_loader.py:197: Unloading HF weight file: /ssd2/models/Phi-3-mini-128k-instruct/model-00001-of-00002.safetensors [2024-06-11 04:46:43] INFO stats.py:77: Time usage: HF loading: 2.547 sec; Pre-quantization mapping: 1.720 sec; Quantization: 2.394 sec [2024-06-11 04:46:43] INFO stats.py:91: RAM usage: Peak RAM: 9.262 GB. Total bytes loaded from disk: 14.235 GB [2024-06-11 04:46:43] INFO convert_weight.py:155: Parameter size after quantization: 2.225 GB [2024-06-11 04:46:43] INFO convert_weight.py:160: Total parameters: 3,821,079,552 [2024-06-11 04:46:43] INFO convert_weight.py:161: Bits per parameter: 5.001 [2024-06-11 04:46:43] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC All finished, 83 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/ndarray-cache.json Also saved a bf16 record to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/ndarray-cache-b16.json /home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm gen_config /ssd2/models/Phi-3-mini-128k-instruct --quantization q4f32_1 --conv-template phi-3 --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC [2024-06-11 04:50:38] INFO auto_config.py:116: Found model configuration: /ssd2/models/Phi-3-mini-128k-instruct/config.json [2024-06-11 04:50:38] INFO auto_config.py:154: Found model type: phi3. Use `--model-type` to override. [2024-06-11 04:50:38] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072) [2024-06-11 04:50:38] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048 [2024-06-11 04:50:38] INFO config.py:107: Overriding max_batch_size from 1 to 80 [2024-06-11 04:50:38] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 1 [2024-06-11 04:50:38] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: [32000, 32001, 32007] [2024-06-11 04:50:38] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 32000 [2024-06-11 04:50:38] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/tokenizer.model. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer.model [2024-06-11 04:50:38] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer.json [2024-06-11 04:50:38] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/vocab.json [2024-06-11 04:50:38] INFO gen_config.py:157: Not found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/merges.txt [2024-06-11 04:50:38] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/added_tokens.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/added_tokens.json [2024-06-11 04:50:38] INFO gen_config.py:155: Found tokenizer config: /ssd2/models/Phi-3-mini-128k-instruct/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/tokenizer_config.json [2024-06-11 04:50:38] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_fallback', 'prepend_space_in_encode': True, 'strip_space_in_decode': True} [2024-06-11 04:50:38] INFO gen_config.py:32: [System default] Setting temperature: 1.0 [2024-06-11 04:50:38] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0 [2024-06-11 04:50:38] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0 [2024-06-11 04:50:38] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0 [2024-06-11 04:50:38] INFO gen_config.py:32: [System default] Setting top_p: 1.0 [2024-06-11 04:50:38] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/mlc-chat-config.json /home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm convert_weight /ssd2/models/Phi-3-mini-128k-instruct --quantization q4f32_1 --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC [2024-06-11 04:50:39] INFO auto_config.py:116: Found model configuration: /ssd2/models/Phi-3-mini-128k-instruct/config.json [2024-06-11 04:50:40] INFO auto_device.py:79: Found device: cuda:0 [2024-06-11 04:50:40] INFO auto_device.py:79: Found device: cuda:1 [2024-06-11 04:50:41] INFO auto_device.py:88: Not found device: rocm:0 [2024-06-11 04:50:42] INFO auto_device.py:88: Not found device: metal:0 [2024-06-11 04:50:43] INFO auto_device.py:79: Found device: vulkan:0 [2024-06-11 04:50:43] INFO auto_device.py:79: Found device: vulkan:1 [2024-06-11 04:50:43] INFO auto_device.py:79: Found device: vulkan:2 [2024-06-11 04:50:44] INFO auto_device.py:88: Not found device: opencl:0 [2024-06-11 04:50:44] INFO auto_device.py:35: Using device: cuda:0 [2024-06-11 04:50:44] INFO auto_weight.py:71: Finding weights in: /ssd2/models/Phi-3-mini-128k-instruct [2024-06-11 04:50:44] INFO auto_weight.py:137: Not found Huggingface PyTorch [2024-06-11 04:50:44] INFO auto_weight.py:144: Found source weight format: huggingface-safetensor. Source configuration: /ssd2/models/Phi-3-mini-128k-instruct/model.safetensors.index.json [2024-06-11 04:50:44] INFO auto_weight.py:107: Using source weight configuration: /ssd2/models/Phi-3-mini-128k-instruct/model.safetensors.index.json. Use `--source` to override. [2024-06-11 04:50:44] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override. [2024-06-11 04:50:44] INFO auto_config.py:154: Found model type: phi3. Use `--model-type` to override. [2024-06-11 04:50:44] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (131072) [2024-06-11 04:50:44] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048 Weight conversion with arguments: --config /ssd2/models/Phi-3-mini-128k-instruct/config.json --quantization GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7) --model-type phi3 --device cuda:0 --source /ssd2/models/Phi-3-mini-128k-instruct/model.safetensors.index.json --source-format huggingface-safetensor --output /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC Start storing to cache /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC 0%| | 0/195 [00:00 type is zero. setattr(self, word, getattr(machar, word).flat[0]) /home/rickzhou/miniconda3/envs/mlc/lib/python3.11/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for type is zero. return self._float_to_str(self.smallest_subnormal) 1%| | 1/195 [00:02<09:11, 2.84s/it] [2024-06-11 04:50:50] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.21.ln.weight", shape: (3072,), dtype: float32 1%| | 1/195 [00:02<09:11, 2.84s/it] [2024-06-11 04:50:50] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 8192), float32, cuda, axis=1, output_transpose=False) 1%| | 1/195 [00:02<09:11, 2.84s/it] [2024-06-11 04:50:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 1%| | 1/195 [00:03<09:11, 2.84s/it] [2024-06-11 04:50:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 1%| | 1/195 [00:03<09:11, 2.84s/it] 2%|▏ | 3/195 [00:03<02:44, 1.17it/s] [2024-06-11 04:50:51] INFO group_quantization.py:217: Compiling quantize function for key: ((16384, 3072), float32, cuda, axis=1, output_transpose=False) 2%|▏ | 3/195 [00:03<02:44, 1.17it/s] [2024-06-11 04:50:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 2%|▏ | 3/195 [00:03<02:44, 1.17it/s] [2024-06-11 04:50:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 2%|▏ | 3/195 [00:03<02:44, 1.17it/s] 2%|▏ | 4/195 [00:03<02:17, 1.39it/s] [2024-06-11 04:50:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.21.post_attention_layernorm.weight", shape: (3072,), dtype: float32 2%|▏ | 4/195 [00:03<02:17, 1.39it/s] [2024-06-11 04:50:51] INFO group_quantization.py:217: Compiling quantize function for key: ((9216, 3072), float32, cuda, axis=1, output_transpose=False) 2%|▏ | 4/195 [00:03<02:17, 1.39it/s] [2024-06-11 04:50:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 2%|▏ | 4/195 [00:03<02:17, 1.39it/s] [2024-06-11 04:50:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 2%|▏ | 4/195 [00:04<02:17, 1.39it/s] 3%|▎ | 6/195 [00:04<01:28, 2.13it/s] [2024-06-11 04:50:51] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.22.ln.weight", shape: (3072,), dtype: float32 3%|▎ | 6/195 [00:04<01:28, 2.13it/s] [2024-06-11 04:50:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 3%|▎ | 6/195 [00:04<01:28, 2.13it/s] [2024-06-11 04:50:51] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 3%|▎ | 6/195 [00:04<01:28, 2.13it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 3%|▎ | 6/195 [00:04<01:28, 2.13it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 3%|▎ | 6/195 [00:04<01:28, 2.13it/s] 5%|▍ | 9/195 [00:04<00:48, 3.84it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.22.post_attention_layernorm.weight", shape: (3072,), dtype: float32 5%|▍ | 9/195 [00:04<00:48, 3.84it/s] [2024-06-11 04:50:52] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 3072), float32, cuda, axis=1, output_transpose=False) 5%|▍ | 9/195 [00:04<00:48, 3.84it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 5%|▍ | 9/195 [00:04<00:48, 3.84it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 5%|▍ | 9/195 [00:04<00:48, 3.84it/s] 6%|▌ | 11/195 [00:04<00:45, 4.04it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 6%|▌ | 11/195 [00:04<00:45, 4.04it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 6%|▌ | 11/195 [00:04<00:45, 4.04it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.23.ln.weight", shape: (3072,), dtype: float32 6%|▌ | 11/195 [00:04<00:45, 4.04it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 6%|▌ | 11/195 [00:04<00:45, 4.04it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 6%|▌ | 11/195 [00:04<00:45, 4.04it/s] 7%|▋ | 14/195 [00:04<00:29, 6.06it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 7%|▋ | 14/195 [00:04<00:29, 6.06it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 7%|▋ | 14/195 [00:04<00:29, 6.06it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.23.post_attention_layernorm.weight", shape: (3072,), dtype: float32 7%|▋ | 14/195 [00:04<00:29, 6.06it/s] 8%|▊ | 16/195 [00:04<00:24, 7.19it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 8%|▊ | 16/195 [00:04<00:24, 7.19it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 8%|▊ | 16/195 [00:04<00:24, 7.19it/s] [2024-06-11 04:50:52] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 8%|▊ | 16/195 [00:05<00:24, 7.19it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 8%|▊ | 16/195 [00:05<00:24, 7.19it/s] 9%|▉ | 18/195 [00:05<00:20, 8.44it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.24.ln.weight", shape: (3072,), dtype: float32 9%|▉ | 18/195 [00:05<00:20, 8.44it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 9%|▉ | 18/195 [00:05<00:20, 8.44it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 9%|▉ | 18/195 [00:05<00:20, 8.44it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 9%|▉ | 18/195 [00:05<00:20, 8.44it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 9%|▉ | 18/195 [00:05<00:20, 8.44it/s] 11%|█ | 21/195 [00:05<00:16, 10.43it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.24.post_attention_layernorm.weight", shape: (3072,), dtype: float32 11%|█ | 21/195 [00:05<00:16, 10.43it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 11%|█ | 21/195 [00:05<00:16, 10.43it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 11%|█ | 21/195 [00:05<00:16, 10.43it/s] 12%|█▏ | 23/195 [00:05<00:14, 11.47it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 12%|█▏ | 23/195 [00:05<00:14, 11.47it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 12%|█▏ | 23/195 [00:05<00:14, 11.47it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.25.ln.weight", shape: (3072,), dtype: float32 12%|█▏ | 23/195 [00:05<00:14, 11.47it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 12%|█▏ | 23/195 [00:05<00:14, 11.47it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 12%|█▏ | 23/195 [00:05<00:14, 11.47it/s] 13%|█▎ | 26/195 [00:05<00:12, 14.05it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 13%|█▎ | 26/195 [00:05<00:12, 14.05it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 13%|█▎ | 26/195 [00:05<00:12, 14.05it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.25.post_attention_layernorm.weight", shape: (3072,), dtype: float32 13%|█▎ | 26/195 [00:05<00:12, 14.05it/s] 14%|█▍ | 28/195 [00:05<00:11, 14.17it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 14%|█▍ | 28/195 [00:05<00:11, 14.17it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 14%|█▍ | 28/195 [00:05<00:11, 14.17it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 14%|█▍ | 28/195 [00:05<00:11, 14.17it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 14%|█▍ | 28/195 [00:05<00:11, 14.17it/s] 15%|█▌ | 30/195 [00:05<00:11, 14.74it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.26.ln.weight", shape: (3072,), dtype: float32 15%|█▌ | 30/195 [00:05<00:11, 14.74it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 15%|█▌ | 30/195 [00:05<00:11, 14.74it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 15%|█▌ | 30/195 [00:05<00:11, 14.74it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 15%|█▌ | 30/195 [00:05<00:11, 14.74it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 15%|█▌ | 30/195 [00:05<00:11, 14.74it/s] 17%|█▋ | 33/195 [00:05<00:10, 15.71it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.26.post_attention_layernorm.weight", shape: (3072,), dtype: float32 17%|█▋ | 33/195 [00:05<00:10, 15.71it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 17%|█▋ | 33/195 [00:05<00:10, 15.71it/s] [2024-06-11 04:50:53] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 17%|█▋ | 33/195 [00:06<00:10, 15.71it/s] 18%|█▊ | 35/195 [00:06<00:10, 15.72it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 18%|█▊ | 35/195 [00:06<00:10, 15.72it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 18%|█▊ | 35/195 [00:06<00:10, 15.72it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.27.ln.weight", shape: (3072,), dtype: float32 18%|█▊ | 35/195 [00:06<00:10, 15.72it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 18%|█▊ | 35/195 [00:06<00:10, 15.72it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 18%|█▊ | 35/195 [00:06<00:10, 15.72it/s] 19%|█▉ | 38/195 [00:06<00:08, 17.92it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 19%|█▉ | 38/195 [00:06<00:08, 17.92it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 19%|█▉ | 38/195 [00:06<00:08, 17.92it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.27.post_attention_layernorm.weight", shape: (3072,), dtype: float32 19%|█▉ | 38/195 [00:06<00:08, 17.92it/s] 21%|██ | 40/195 [00:06<00:09, 16.95it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 21%|██ | 40/195 [00:06<00:09, 16.95it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 21%|██ | 40/195 [00:06<00:09, 16.95it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 21%|██ | 40/195 [00:06<00:09, 16.95it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 21%|██ | 40/195 [00:06<00:09, 16.95it/s] 22%|██▏ | 42/195 [00:06<00:09, 16.38it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.28.ln.weight", shape: (3072,), dtype: float32 22%|██▏ | 42/195 [00:06<00:09, 16.38it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 22%|██▏ | 42/195 [00:06<00:09, 16.38it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 22%|██▏ | 42/195 [00:06<00:09, 16.38it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 22%|██▏ | 42/195 [00:06<00:09, 16.38it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 22%|██▏ | 42/195 [00:06<00:09, 16.38it/s] 23%|██▎ | 45/195 [00:06<00:08, 17.12it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.28.post_attention_layernorm.weight", shape: (3072,), dtype: float32 23%|██▎ | 45/195 [00:06<00:08, 17.12it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 23%|██▎ | 45/195 [00:06<00:08, 17.12it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 23%|██▎ | 45/195 [00:06<00:08, 17.12it/s] 24%|██▍ | 47/195 [00:06<00:08, 16.66it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 24%|██▍ | 47/195 [00:06<00:08, 16.66it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 24%|██▍ | 47/195 [00:06<00:08, 16.66it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.29.ln.weight", shape: (3072,), dtype: float32 24%|██▍ | 47/195 [00:06<00:08, 16.66it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 24%|██▍ | 47/195 [00:06<00:08, 16.66it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 24%|██▍ | 47/195 [00:06<00:08, 16.66it/s] 26%|██▌ | 50/195 [00:06<00:07, 18.74it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 26%|██▌ | 50/195 [00:06<00:07, 18.74it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 26%|██▌ | 50/195 [00:07<00:07, 18.74it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.29.post_attention_layernorm.weight", shape: (3072,), dtype: float32 26%|██▌ | 50/195 [00:07<00:07, 18.74it/s] 27%|██▋ | 52/195 [00:07<00:08, 17.51it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 27%|██▋ | 52/195 [00:07<00:08, 17.51it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 27%|██▋ | 52/195 [00:07<00:08, 17.51it/s] [2024-06-11 04:50:54] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 27%|██▋ | 52/195 [00:07<00:08, 17.51it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 27%|██▋ | 52/195 [00:07<00:08, 17.51it/s] 28%|██▊ | 54/195 [00:07<00:08, 17.21it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.30.ln.weight", shape: (3072,), dtype: float32 28%|██▊ | 54/195 [00:07<00:08, 17.21it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 28%|██▊ | 54/195 [00:07<00:08, 17.21it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 28%|██▊ | 54/195 [00:07<00:08, 17.21it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 28%|██▊ | 54/195 [00:07<00:08, 17.21it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 28%|██▊ | 54/195 [00:07<00:08, 17.21it/s] 29%|██▉ | 57/195 [00:07<00:07, 17.76it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.30.post_attention_layernorm.weight", shape: (3072,), dtype: float32 29%|██▉ | 57/195 [00:07<00:07, 17.76it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 29%|██▉ | 57/195 [00:07<00:07, 17.76it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 29%|██▉ | 57/195 [00:07<00:07, 17.76it/s] 30%|███ | 59/195 [00:07<00:07, 17.30it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 30%|███ | 59/195 [00:07<00:07, 17.30it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 30%|███ | 59/195 [00:07<00:07, 17.30it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.31.ln.weight", shape: (3072,), dtype: float32 30%|███ | 59/195 [00:07<00:07, 17.30it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 30%|███ | 59/195 [00:07<00:07, 17.30it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 30%|███ | 59/195 [00:07<00:07, 17.30it/s] 32%|███▏ | 62/195 [00:07<00:06, 19.24it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 32%|███▏ | 62/195 [00:07<00:06, 19.24it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 32%|███▏ | 62/195 [00:07<00:06, 19.24it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.31.post_attention_layernorm.weight", shape: (3072,), dtype: float32 32%|███▏ | 62/195 [00:07<00:06, 19.24it/s] 33%|███▎ | 64/195 [00:07<00:07, 17.80it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 33%|███▎ | 64/195 [00:07<00:07, 17.80it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 33%|███▎ | 64/195 [00:07<00:07, 17.80it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 33%|███▎ | 64/195 [00:07<00:07, 17.80it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 33%|███▎ | 64/195 [00:07<00:07, 17.80it/s] 34%|███▍ | 66/195 [00:07<00:07, 17.42it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.norm.weight", shape: (3072,), dtype: float32 34%|███▍ | 66/195 [00:07<00:07, 17.42it/s] [2024-06-11 04:50:55] INFO huggingface_loader.py:197: Unloading HF weight file: /ssd2/models/Phi-3-mini-128k-instruct/model-00002-of-00002.safetensors 34%|███▍ | 66/195 [00:07<00:07, 17.42it/s] [2024-06-11 04:50:56] INFO huggingface_loader.py:185: Loading HF parameters from: /ssd2/models/Phi-3-mini-128k-instruct/model-00001-of-00002.safetensors 34%|███▍ | 66/195 [00:08<00:07, 17.42it/s] [2024-06-11 04:50:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.embd.q_weight", shape: (32064, 384), dtype: uint32 34%|███▍ | 66/195 [00:08<00:07, 17.42it/s] [2024-06-11 04:50:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.embd.q_scale", shape: (32064, 96), dtype: float32 34%|███▍ | 66/195 [00:08<00:07, 17.42it/s] 35%|███▍ | 68/195 [00:08<00:24, 5.15it/s] [2024-06-11 04:50:56] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.0.ln.weight", shape: (3072,), dtype: float32 35%|███▍ | 68/195 [00:08<00:24, 5.15it/s] [2024-06-11 04:50:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 35%|███▍ | 68/195 [00:08<00:24, 5.15it/s] [2024-06-11 04:50:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 35%|███▍ | 68/195 [00:09<00:24, 5.15it/s] 36%|███▌ | 70/195 [00:09<00:19, 6.46it/s] [2024-06-11 04:50:56] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 36%|███▌ | 70/195 [00:09<00:19, 6.46it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 36%|███▌ | 70/195 [00:09<00:19, 6.46it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.0.post_attention_layernorm.weight", shape: (3072,), dtype: float32 36%|███▌ | 70/195 [00:09<00:19, 6.46it/s] 37%|███▋ | 72/195 [00:09<00:16, 7.66it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 37%|███▋ | 72/195 [00:09<00:16, 7.66it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 37%|███▋ | 72/195 [00:09<00:16, 7.66it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 37%|███▋ | 72/195 [00:09<00:16, 7.66it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.0.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 37%|███▋ | 72/195 [00:09<00:16, 7.66it/s] 38%|███▊ | 74/195 [00:09<00:13, 9.15it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.1.ln.weight", shape: (3072,), dtype: float32 38%|███▊ | 74/195 [00:09<00:13, 9.15it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 38%|███▊ | 74/195 [00:09<00:13, 9.15it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 38%|███▊ | 74/195 [00:09<00:13, 9.15it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 38%|███▊ | 74/195 [00:09<00:13, 9.15it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 38%|███▊ | 74/195 [00:09<00:13, 9.15it/s] 39%|███▉ | 77/195 [00:09<00:10, 11.16it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.1.post_attention_layernorm.weight", shape: (3072,), dtype: float32 39%|███▉ | 77/195 [00:09<00:10, 11.16it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 39%|███▉ | 77/195 [00:09<00:10, 11.16it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 39%|███▉ | 77/195 [00:09<00:10, 11.16it/s] 41%|████ | 79/195 [00:09<00:09, 12.07it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 41%|████ | 79/195 [00:09<00:09, 12.07it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.1.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 41%|████ | 79/195 [00:09<00:09, 12.07it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.10.ln.weight", shape: (3072,), dtype: float32 41%|████ | 79/195 [00:09<00:09, 12.07it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 41%|████ | 79/195 [00:09<00:09, 12.07it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 41%|████ | 79/195 [00:09<00:09, 12.07it/s] 42%|████▏ | 82/195 [00:09<00:07, 14.53it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 42%|████▏ | 82/195 [00:09<00:07, 14.53it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 42%|████▏ | 82/195 [00:09<00:07, 14.53it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.10.post_attention_layernorm.weight", shape: (3072,), dtype: float32 42%|████▏ | 82/195 [00:09<00:07, 14.53it/s] 43%|████▎ | 84/195 [00:09<00:08, 13.86it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 43%|████▎ | 84/195 [00:09<00:08, 13.86it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 43%|████▎ | 84/195 [00:09<00:08, 13.86it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 43%|████▎ | 84/195 [00:09<00:08, 13.86it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.10.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 43%|████▎ | 84/195 [00:10<00:08, 13.86it/s] 44%|████▍ | 86/195 [00:10<00:07, 14.55it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.11.ln.weight", shape: (3072,), dtype: float32 44%|████▍ | 86/195 [00:10<00:07, 14.55it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 44%|████▍ | 86/195 [00:10<00:07, 14.55it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 44%|████▍ | 86/195 [00:10<00:07, 14.55it/s] [2024-06-11 04:50:57] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 44%|████▍ | 86/195 [00:10<00:07, 14.55it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 44%|████▍ | 86/195 [00:10<00:07, 14.55it/s] 46%|████▌ | 89/195 [00:10<00:06, 15.26it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.11.post_attention_layernorm.weight", shape: (3072,), dtype: float32 46%|████▌ | 89/195 [00:10<00:06, 15.26it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 46%|████▌ | 89/195 [00:10<00:06, 15.26it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 46%|████▌ | 89/195 [00:10<00:06, 15.26it/s] 47%|████▋ | 91/195 [00:10<00:06, 15.04it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 47%|████▋ | 91/195 [00:10<00:06, 15.04it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.11.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 47%|████▋ | 91/195 [00:10<00:06, 15.04it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.12.ln.weight", shape: (3072,), dtype: float32 47%|████▋ | 91/195 [00:10<00:06, 15.04it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 47%|████▋ | 91/195 [00:10<00:06, 15.04it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 47%|████▋ | 91/195 [00:10<00:06, 15.04it/s] 48%|████▊ | 94/195 [00:10<00:05, 17.14it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 48%|████▊ | 94/195 [00:10<00:05, 17.14it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 48%|████▊ | 94/195 [00:10<00:05, 17.14it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.12.post_attention_layernorm.weight", shape: (3072,), dtype: float32 48%|████▊ | 94/195 [00:10<00:05, 17.14it/s] 49%|████▉ | 96/195 [00:10<00:06, 16.28it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 49%|████▉ | 96/195 [00:10<00:06, 16.28it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 49%|████▉ | 96/195 [00:10<00:06, 16.28it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 49%|████▉ | 96/195 [00:10<00:06, 16.28it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.12.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 49%|████▉ | 96/195 [00:10<00:06, 16.28it/s] 50%|█████ | 98/195 [00:10<00:05, 16.47it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.13.ln.weight", shape: (3072,), dtype: float32 50%|█████ | 98/195 [00:10<00:05, 16.47it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 50%|█████ | 98/195 [00:10<00:05, 16.47it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 50%|█████ | 98/195 [00:10<00:05, 16.47it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 50%|█████ | 98/195 [00:10<00:05, 16.47it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 50%|█████ | 98/195 [00:10<00:05, 16.47it/s] 52%|█████▏ | 101/195 [00:10<00:05, 16.68it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.13.post_attention_layernorm.weight", shape: (3072,), dtype: float32 52%|█████▏ | 101/195 [00:10<00:05, 16.68it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 52%|█████▏ | 101/195 [00:10<00:05, 16.68it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 52%|█████▏ | 101/195 [00:11<00:05, 16.68it/s] 53%|█████▎ | 103/195 [00:11<00:05, 16.04it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 53%|█████▎ | 103/195 [00:11<00:05, 16.04it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.13.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 53%|█████▎ | 103/195 [00:11<00:05, 16.04it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.14.ln.weight", shape: (3072,), dtype: float32 53%|█████▎ | 103/195 [00:11<00:05, 16.04it/s] [2024-06-11 04:50:58] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 53%|█████▎ | 103/195 [00:11<00:05, 16.04it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 53%|█████▎ | 103/195 [00:11<00:05, 16.04it/s] 54%|█████▍ | 106/195 [00:11<00:04, 17.92it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 54%|█████▍ | 106/195 [00:11<00:04, 17.92it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 54%|█████▍ | 106/195 [00:11<00:04, 17.92it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.14.post_attention_layernorm.weight", shape: (3072,), dtype: float32 54%|█████▍ | 106/195 [00:11<00:04, 17.92it/s] 55%|█████▌ | 108/195 [00:11<00:05, 16.81it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 55%|█████▌ | 108/195 [00:11<00:05, 16.81it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 55%|█████▌ | 108/195 [00:11<00:05, 16.81it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 55%|█████▌ | 108/195 [00:11<00:05, 16.81it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.14.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 55%|█████▌ | 108/195 [00:11<00:05, 16.81it/s] 56%|█████▋ | 110/195 [00:11<00:05, 16.89it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.15.ln.weight", shape: (3072,), dtype: float32 56%|█████▋ | 110/195 [00:11<00:05, 16.89it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 56%|█████▋ | 110/195 [00:11<00:05, 16.89it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 56%|█████▋ | 110/195 [00:11<00:05, 16.89it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 56%|█████▋ | 110/195 [00:11<00:05, 16.89it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 56%|█████▋ | 110/195 [00:11<00:05, 16.89it/s] 58%|█████▊ | 113/195 [00:11<00:04, 16.65it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.15.post_attention_layernorm.weight", shape: (3072,), dtype: float32 58%|█████▊ | 113/195 [00:11<00:04, 16.65it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 58%|█████▊ | 113/195 [00:11<00:04, 16.65it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 58%|█████▊ | 113/195 [00:11<00:04, 16.65it/s] 59%|█████▉ | 115/195 [00:11<00:04, 16.13it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 59%|█████▉ | 115/195 [00:11<00:04, 16.13it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.15.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 59%|█████▉ | 115/195 [00:11<00:04, 16.13it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.16.ln.weight", shape: (3072,), dtype: float32 59%|█████▉ | 115/195 [00:11<00:04, 16.13it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 59%|█████▉ | 115/195 [00:11<00:04, 16.13it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 59%|█████▉ | 115/195 [00:11<00:04, 16.13it/s] 61%|██████ | 118/195 [00:11<00:04, 17.92it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 61%|██████ | 118/195 [00:11<00:04, 17.92it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 61%|██████ | 118/195 [00:12<00:04, 17.92it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.16.post_attention_layernorm.weight", shape: (3072,), dtype: float32 61%|██████ | 118/195 [00:12<00:04, 17.92it/s] 62%|██████▏ | 120/195 [00:12<00:04, 16.78it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 62%|██████▏ | 120/195 [00:12<00:04, 16.78it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 62%|██████▏ | 120/195 [00:12<00:04, 16.78it/s] [2024-06-11 04:50:59] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 62%|██████▏ | 120/195 [00:12<00:04, 16.78it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.16.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 62%|██████▏ | 120/195 [00:12<00:04, 16.78it/s] 63%|██████▎ | 122/195 [00:12<00:04, 16.84it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.17.ln.weight", shape: (3072,), dtype: float32 63%|██████▎ | 122/195 [00:12<00:04, 16.84it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 63%|██████▎ | 122/195 [00:12<00:04, 16.84it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 63%|██████▎ | 122/195 [00:12<00:04, 16.84it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 63%|██████▎ | 122/195 [00:12<00:04, 16.84it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 63%|██████▎ | 122/195 [00:12<00:04, 16.84it/s] 64%|██████▍ | 125/195 [00:12<00:04, 16.55it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.17.post_attention_layernorm.weight", shape: (3072,), dtype: float32 64%|██████▍ | 125/195 [00:12<00:04, 16.55it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 64%|██████▍ | 125/195 [00:12<00:04, 16.55it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 64%|██████▍ | 125/195 [00:12<00:04, 16.55it/s] 65%|██████▌ | 127/195 [00:12<00:04, 16.32it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 65%|██████▌ | 127/195 [00:12<00:04, 16.32it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.17.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 65%|██████▌ | 127/195 [00:12<00:04, 16.32it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.18.ln.weight", shape: (3072,), dtype: float32 65%|██████▌ | 127/195 [00:12<00:04, 16.32it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 65%|██████▌ | 127/195 [00:12<00:04, 16.32it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 65%|██████▌ | 127/195 [00:12<00:04, 16.32it/s] 67%|██████▋ | 130/195 [00:12<00:03, 18.17it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 67%|██████▋ | 130/195 [00:12<00:03, 18.17it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 67%|██████▋ | 130/195 [00:12<00:03, 18.17it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.18.post_attention_layernorm.weight", shape: (3072,), dtype: float32 67%|██████▋ | 130/195 [00:12<00:03, 18.17it/s] 68%|██████▊ | 132/195 [00:12<00:03, 16.90it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 68%|██████▊ | 132/195 [00:12<00:03, 16.90it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 68%|██████▊ | 132/195 [00:12<00:03, 16.90it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 68%|██████▊ | 132/195 [00:12<00:03, 16.90it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.18.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 68%|██████▊ | 132/195 [00:12<00:03, 16.90it/s] 69%|██████▊ | 134/195 [00:12<00:03, 16.98it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.19.ln.weight", shape: (3072,), dtype: float32 69%|██████▊ | 134/195 [00:12<00:03, 16.98it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 69%|██████▊ | 134/195 [00:12<00:03, 16.98it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 69%|██████▊ | 134/195 [00:12<00:03, 16.98it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 69%|██████▊ | 134/195 [00:12<00:03, 16.98it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 69%|██████▊ | 134/195 [00:13<00:03, 16.98it/s] 70%|███████ | 137/195 [00:13<00:03, 16.93it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.19.post_attention_layernorm.weight", shape: (3072,), dtype: float32 70%|███████ | 137/195 [00:13<00:03, 16.93it/s] [2024-06-11 04:51:00] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 70%|███████ | 137/195 [00:13<00:03, 16.93it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 70%|███████ | 137/195 [00:13<00:03, 16.93it/s] 71%|███████▏ | 139/195 [00:13<00:03, 16.30it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 71%|███████▏ | 139/195 [00:13<00:03, 16.30it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.19.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 71%|███████▏ | 139/195 [00:13<00:03, 16.30it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.2.ln.weight", shape: (3072,), dtype: float32 71%|███████▏ | 139/195 [00:13<00:03, 16.30it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 71%|███████▏ | 139/195 [00:13<00:03, 16.30it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 71%|███████▏ | 139/195 [00:13<00:03, 16.30it/s] 73%|███████▎ | 142/195 [00:13<00:02, 18.12it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 73%|███████▎ | 142/195 [00:13<00:02, 18.12it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 73%|███████▎ | 142/195 [00:13<00:02, 18.12it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.2.post_attention_layernorm.weight", shape: (3072,), dtype: float32 73%|███████▎ | 142/195 [00:13<00:02, 18.12it/s] 74%|███████▍ | 144/195 [00:13<00:03, 16.86it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 74%|███████▍ | 144/195 [00:13<00:03, 16.86it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 74%|███████▍ | 144/195 [00:13<00:03, 16.86it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 74%|███████▍ | 144/195 [00:13<00:03, 16.86it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.2.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 74%|███████▍ | 144/195 [00:13<00:03, 16.86it/s] 75%|███████▍ | 146/195 [00:13<00:02, 16.89it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.20.ln.weight", shape: (3072,), dtype: float32 75%|███████▍ | 146/195 [00:13<00:02, 16.89it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 75%|███████▍ | 146/195 [00:13<00:02, 16.89it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 75%|███████▍ | 146/195 [00:13<00:02, 16.89it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 75%|███████▍ | 146/195 [00:13<00:02, 16.89it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 75%|███████▍ | 146/195 [00:13<00:02, 16.89it/s] 76%|███████▋ | 149/195 [00:13<00:02, 16.66it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.20.post_attention_layernorm.weight", shape: (3072,), dtype: float32 76%|███████▋ | 149/195 [00:13<00:02, 16.66it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 76%|███████▋ | 149/195 [00:13<00:02, 16.66it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 76%|███████▋ | 149/195 [00:13<00:02, 16.66it/s] 77%|███████▋ | 151/195 [00:13<00:02, 15.88it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 77%|███████▋ | 151/195 [00:13<00:02, 15.88it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.20.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 77%|███████▋ | 151/195 [00:13<00:02, 15.88it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 77%|███████▋ | 151/195 [00:13<00:02, 15.88it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.21.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 77%|███████▋ | 151/195 [00:13<00:02, 15.88it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.3.ln.weight", shape: (3072,), dtype: float32 77%|███████▋ | 151/195 [00:13<00:02, 15.88it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 77%|███████▋ | 151/195 [00:13<00:02, 15.88it/s] [2024-06-11 04:51:01] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 77%|███████▋ | 151/195 [00:14<00:02, 15.88it/s] 79%|███████▉ | 155/195 [00:14<00:02, 18.00it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 79%|███████▉ | 155/195 [00:14<00:02, 18.00it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 79%|███████▉ | 155/195 [00:14<00:02, 18.00it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.3.post_attention_layernorm.weight", shape: (3072,), dtype: float32 79%|███████▉ | 155/195 [00:14<00:02, 18.00it/s] 81%|████████ | 157/195 [00:14<00:02, 16.94it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 81%|████████ | 157/195 [00:14<00:02, 16.94it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 81%|████████ | 157/195 [00:14<00:02, 16.94it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 81%|████████ | 157/195 [00:14<00:02, 16.94it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.3.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 81%|████████ | 157/195 [00:14<00:02, 16.94it/s] 82%|████████▏ | 159/195 [00:14<00:02, 16.80it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.4.ln.weight", shape: (3072,), dtype: float32 82%|████████▏ | 159/195 [00:14<00:02, 16.80it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 82%|████████▏ | 159/195 [00:14<00:02, 16.80it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 82%|████████▏ | 159/195 [00:14<00:02, 16.80it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 82%|████████▏ | 159/195 [00:14<00:02, 16.80it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 82%|████████▏ | 159/195 [00:14<00:02, 16.80it/s] 83%|████████▎ | 162/195 [00:14<00:01, 16.67it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.4.post_attention_layernorm.weight", shape: (3072,), dtype: float32 83%|████████▎ | 162/195 [00:14<00:01, 16.67it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 83%|████████▎ | 162/195 [00:14<00:01, 16.67it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 83%|████████▎ | 162/195 [00:14<00:01, 16.67it/s] 84%|████████▍ | 164/195 [00:14<00:01, 16.15it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 84%|████████▍ | 164/195 [00:14<00:01, 16.15it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.4.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 84%|████████▍ | 164/195 [00:14<00:01, 16.15it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.5.ln.weight", shape: (3072,), dtype: float32 84%|████████▍ | 164/195 [00:14<00:01, 16.15it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 84%|████████▍ | 164/195 [00:14<00:01, 16.15it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 84%|████████▍ | 164/195 [00:14<00:01, 16.15it/s] 86%|████████▌ | 167/195 [00:14<00:01, 17.94it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 86%|████████▌ | 167/195 [00:14<00:01, 17.94it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 86%|████████▌ | 167/195 [00:14<00:01, 17.94it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.5.post_attention_layernorm.weight", shape: (3072,), dtype: float32 86%|████████▌ | 167/195 [00:14<00:01, 17.94it/s] 87%|████████▋ | 169/195 [00:14<00:01, 16.78it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 87%|████████▋ | 169/195 [00:14<00:01, 16.78it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 87%|████████▋ | 169/195 [00:14<00:01, 16.78it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 87%|████████▋ | 169/195 [00:14<00:01, 16.78it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.5.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 87%|████████▋ | 169/195 [00:15<00:01, 16.78it/s] 88%|████████▊ | 171/195 [00:15<00:01, 16.57it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.6.ln.weight", shape: (3072,), dtype: float32 88%|████████▊ | 171/195 [00:15<00:01, 16.57it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 88%|████████▊ | 171/195 [00:15<00:01, 16.57it/s] [2024-06-11 04:51:02] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 88%|████████▊ | 171/195 [00:15<00:01, 16.57it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 88%|████████▊ | 171/195 [00:15<00:01, 16.57it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 88%|████████▊ | 171/195 [00:15<00:01, 16.57it/s] 89%|████████▉ | 174/195 [00:15<00:01, 16.95it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.6.post_attention_layernorm.weight", shape: (3072,), dtype: float32 89%|████████▉ | 174/195 [00:15<00:01, 16.95it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 89%|████████▉ | 174/195 [00:15<00:01, 16.95it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 89%|████████▉ | 174/195 [00:15<00:01, 16.95it/s] 90%|█████████ | 176/195 [00:15<00:01, 16.48it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 90%|█████████ | 176/195 [00:15<00:01, 16.48it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.6.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 90%|█████████ | 176/195 [00:15<00:01, 16.48it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.7.ln.weight", shape: (3072,), dtype: float32 90%|█████████ | 176/195 [00:15<00:01, 16.48it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 90%|█████████ | 176/195 [00:15<00:01, 16.48it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 90%|█████████ | 176/195 [00:15<00:01, 16.48it/s] 92%|█████████▏| 179/195 [00:15<00:00, 18.17it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 92%|█████████▏| 179/195 [00:15<00:00, 18.17it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 92%|█████████▏| 179/195 [00:15<00:00, 18.17it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.7.post_attention_layernorm.weight", shape: (3072,), dtype: float32 92%|█████████▏| 179/195 [00:15<00:00, 18.17it/s] 93%|█████████▎| 181/195 [00:15<00:00, 16.97it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 93%|█████████▎| 181/195 [00:15<00:00, 16.97it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 93%|█████████▎| 181/195 [00:15<00:00, 16.97it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 93%|█████████▎| 181/195 [00:15<00:00, 16.97it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.7.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 93%|█████████▎| 181/195 [00:15<00:00, 16.97it/s] 94%|█████████▍| 183/195 [00:15<00:00, 16.98it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.8.ln.weight", shape: (3072,), dtype: float32 94%|█████████▍| 183/195 [00:15<00:00, 16.98it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 94%|█████████▍| 183/195 [00:15<00:00, 16.98it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 94%|█████████▍| 183/195 [00:15<00:00, 16.98it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 94%|█████████▍| 183/195 [00:15<00:00, 16.98it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 94%|█████████▍| 183/195 [00:15<00:00, 16.98it/s] 95%|█████████▌| 186/195 [00:15<00:00, 17.46it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.8.post_attention_layernorm.weight", shape: (3072,), dtype: float32 95%|█████████▌| 186/195 [00:15<00:00, 17.46it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 95%|█████████▌| 186/195 [00:15<00:00, 17.46it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 95%|█████████▌| 186/195 [00:16<00:00, 17.46it/s] 96%|█████████▋| 188/195 [00:16<00:00, 16.82it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 96%|█████████▋| 188/195 [00:16<00:00, 16.82it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.8.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 96%|█████████▋| 188/195 [00:16<00:00, 16.82it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.9.ln.weight", shape: (3072,), dtype: float32 96%|█████████▋| 188/195 [00:16<00:00, 16.82it/s] [2024-06-11 04:51:03] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32 96%|█████████▋| 188/195 [00:16<00:00, 16.82it/s] [2024-06-11 04:51:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32 96%|█████████▋| 188/195 [00:16<00:00, 16.82it/s] 98%|█████████▊| 191/195 [00:16<00:00, 18.46it/s] [2024-06-11 04:51:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32 98%|█████████▊| 191/195 [00:16<00:00, 18.46it/s] [2024-06-11 04:51:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32 98%|█████████▊| 191/195 [00:16<00:00, 18.46it/s] [2024-06-11 04:51:04] INFO huggingface_loader.py:175: [Not quantized] Parameter: "transformer.h.9.post_attention_layernorm.weight", shape: (3072,), dtype: float32 98%|█████████▊| 191/195 [00:16<00:00, 18.46it/s] 99%|█████████▉| 193/195 [00:16<00:00, 17.10it/s] [2024-06-11 04:51:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32 99%|█████████▉| 193/195 [00:16<00:00, 17.10it/s] [2024-06-11 04:51:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32 99%|█████████▉| 193/195 [00:16<00:00, 17.10it/s] [2024-06-11 04:51:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32 99%|█████████▉| 193/195 [00:16<00:00, 17.10it/s] [2024-06-11 04:51:04] INFO huggingface_loader.py:167: [Quantized] Parameter: "transformer.h.9.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32 99%|█████████▉| 193/195 [00:16<00:00, 17.10it/s] 100%|██████████| 195/195 [00:16<00:00, 17.08it/s] 100%|██████████| 195/195 [00:16<00:00, 11.86it/s] [2024-06-11 04:51:04] INFO huggingface_loader.py:197: Unloading HF weight file: /ssd2/models/Phi-3-mini-128k-instruct/model-00001-of-00002.safetensors [2024-06-11 04:51:04] INFO stats.py:77: Time usage: HF loading: 2.537 sec; Pre-quantization mapping: 1.729 sec; Quantization: 2.381 sec [2024-06-11 04:51:04] INFO stats.py:91: RAM usage: Peak RAM: 9.262 GB. Total bytes loaded from disk: 14.235 GB [2024-06-11 04:51:04] INFO convert_weight.py:155: Parameter size after quantization: 2.225 GB [2024-06-11 04:51:04] INFO convert_weight.py:160: Total parameters: 3,821,079,552 [2024-06-11 04:51:04] INFO convert_weight.py:161: Bits per parameter: 5.001 [2024-06-11 04:51:04] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC All finished, 83 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/ndarray-cache.json Also saved a bf16 record to /models/mlc-delivery/hf/mlc-ai/Phi-3-mini-128k-instruct-q4f32_1-MLC/ndarray-cache-b16.json