File size: 47,120 Bytes
0ae60e0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 |
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/TinyLlama-1.1B-Chat-v1.0 --quantization q0f16 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC [2024-06-04 20:08:25] INFO auto_config.py:116: [92mFound[0m model configuration: /models/TinyLlama-1.1B-Chat-v1.0/config.json [2024-06-04 20:08:25] INFO auto_config.py:154: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override. [2024-06-04 20:08:25] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (2048) [2024-06-04 20:08:25] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to 2048 [2024-06-04 20:08:25] INFO config.py:107: Overriding [1mmax_batch_size[0m from 1 to 80 [2024-06-04 20:08:25] INFO gen_config.py:143: [generation_config.json] Setting [1mbos_token_id[0m: 1 [2024-06-04 20:08:25] INFO gen_config.py:143: [generation_config.json] Setting [1meos_token_id[0m: 2 [2024-06-04 20:08:25] INFO gen_config.py:143: [generation_config.json] Setting [1mpad_token_id[0m: 0 [2024-06-04 20:08:25] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/tokenizer.model. Copying to [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/tokenizer.model[0m [2024-06-04 20:08:25] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/tokenizer.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/tokenizer.json[0m [2024-06-04 20:08:25] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/vocab.json [2024-06-04 20:08:25] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/merges.txt [2024-06-04 20:08:25] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/added_tokens.json [2024-06-04 20:08:25] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/tokenizer_config.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/tokenizer_config.json[0m [2024-06-04 20:08:25] 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 20:08:25] INFO gen_config.py:32: [System default] Setting [1mtemperature[0m: 1.0 [2024-06-04 20:08:25] INFO gen_config.py:32: [System default] Setting [1mpresence_penalty[0m: 0.0 [2024-06-04 20:08:25] INFO gen_config.py:32: [System default] Setting [1mfrequency_penalty[0m: 0.0 [2024-06-04 20:08:25] INFO gen_config.py:32: [System default] Setting [1mrepetition_penalty[0m: 1.0 [2024-06-04 20:08:25] INFO gen_config.py:32: [System default] Setting [1mtop_p[0m: 1.0 [2024-06-04 20:08:25] INFO gen_config.py:223: Dumping configuration file to: [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/mlc-chat-config.json[0m /opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/TinyLlama-1.1B-Chat-v1.0 --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC [2024-06-04 20:08:27] INFO auto_config.py:116: [92mFound[0m model configuration: /models/TinyLlama-1.1B-Chat-v1.0/config.json [2024-06-04 20:08:28] INFO auto_device.py:79: [92mFound[0m device: cuda:0 [2024-06-04 20:08:30] INFO auto_device.py:88: [91mNot found[0m device: rocm:0 [2024-06-04 20:08:31] INFO auto_device.py:88: [91mNot found[0m device: metal:0 [2024-06-04 20:08:33] INFO auto_device.py:79: [92mFound[0m device: vulkan:0 [2024-06-04 20:08:33] INFO auto_device.py:79: [92mFound[0m device: vulkan:1 [2024-06-04 20:08:33] INFO auto_device.py:79: [92mFound[0m device: vulkan:2 [2024-06-04 20:08:33] INFO auto_device.py:79: [92mFound[0m device: vulkan:3 [2024-06-04 20:08:34] INFO auto_device.py:88: [91mNot found[0m device: opencl:0 [2024-06-04 20:08:34] INFO auto_device.py:35: Using device: [1mcuda:0[0m [2024-06-04 20:08:34] INFO auto_weight.py:71: Finding weights in: /models/TinyLlama-1.1B-Chat-v1.0 [2024-06-04 20:08:34] INFO auto_weight.py:137: [91mNot found[0m Huggingface PyTorch [2024-06-04 20:08:34] INFO auto_weight.py:144: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors.index.json [2024-06-04 20:08:34] INFO auto_weight.py:107: Using source weight configuration: [1m/models/TinyLlama-1.1B-Chat-v1.0/model.safetensors.index.json[0m. Use `--source` to override. [2024-06-04 20:08:34] INFO auto_weight.py:111: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override. [2024-06-04 20:08:34] INFO auto_config.py:154: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override. [2024-06-04 20:08:34] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (2048) [2024-06-04 20:08:34] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to 2048 [1mWeight conversion with arguments:[0m [1m--config[0m /models/TinyLlama-1.1B-Chat-v1.0/config.json [1m--quantization[0m NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16') [1m--model-type[0m llama [1m--device[0m cuda:0 [1m--source[0m /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors.index.json [1m--source-format[0m huggingface-safetensor [1m--output[0m /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC Start storing to cache /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC 0%| | 0/135 [00:00<?, ?it/s] [2024-06-04 20:08:36] INFO huggingface_loader.py:185: Loading HF parameters from: /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors 0%| | 0/135 [00:00<?, ?it/s] [2024-06-04 20:08:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mlm_head.weight[0m", shape: (32000, 2048), dtype: float16 0%| | 0/135 [00:03<?, ?it/s] 1%| | 1/135 [00:04<09:19, 4.17s/it] [2024-06-04 20:08:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.embed_tokens.weight[0m", shape: (32000, 2048), dtype: float16 1%| | 1/135 [00:04<09:19, 4.17s/it] 1%|β | 2/135 [00:04<04:37, 2.09s/it] [2024-06-04 20:08:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.weight[0m", shape: (2048,), dtype: float16 1%|β | 2/135 [00:04<04:37, 2.09s/it] [2024-06-04 20:08:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 1%|β | 2/135 [00:04<04:37, 2.09s/it] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 1%|β | 2/135 [00:04<04:37, 2.09s/it] 4%|β | 5/135 [00:05<01:27, 1.48it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 4%|β | 5/135 [00:05<01:27, 1.48it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 4%|β | 5/135 [00:05<01:27, 1.48it/s] 5%|β | 7/135 [00:05<00:54, 2.36it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 5%|β | 7/135 [00:05<00:54, 2.36it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.weight[0m", shape: (2048,), dtype: float16 5%|β | 7/135 [00:05<00:54, 2.36it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 5%|β | 7/135 [00:05<00:54, 2.36it/s] 7%|β | 10/135 [00:05<00:30, 4.08it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 7%|β | 10/135 [00:05<00:30, 4.08it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 7%|β | 10/135 [00:05<00:30, 4.08it/s] 9%|β | 12/135 [00:05<00:24, 4.93it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 9%|β | 12/135 [00:05<00:24, 4.93it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 9%|β | 12/135 [00:05<00:24, 4.93it/s] 10%|β | 14/135 [00:05<00:19, 6.36it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.weight[0m", shape: (2048,), dtype: float16 10%|β | 14/135 [00:05<00:19, 6.36it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 10%|β | 14/135 [00:05<00:19, 6.36it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 10%|β | 14/135 [00:05<00:19, 6.36it/s] 13%|ββ | 17/135 [00:05<00:15, 7.70it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 13%|ββ | 17/135 [00:05<00:15, 7.70it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 13%|ββ | 17/135 [00:05<00:15, 7.70it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 13%|ββ | 17/135 [00:06<00:15, 7.70it/s] 15%|ββ | 20/135 [00:06<00:11, 10.40it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.weight[0m", shape: (2048,), dtype: float16 15%|ββ | 20/135 [00:06<00:11, 10.40it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 15%|ββ | 20/135 [00:06<00:11, 10.40it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 15%|ββ | 20/135 [00:06<00:11, 10.40it/s] 17%|ββ | 23/135 [00:06<00:11, 10.16it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 17%|ββ | 23/135 [00:06<00:11, 10.16it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 17%|ββ | 23/135 [00:06<00:11, 10.16it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 17%|ββ | 23/135 [00:06<00:11, 10.16it/s] 19%|ββ | 26/135 [00:06<00:08, 12.86it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.weight[0m", shape: (2048,), dtype: float16 19%|ββ | 26/135 [00:06<00:08, 12.86it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 19%|ββ | 26/135 [00:06<00:08, 12.86it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 19%|ββ | 26/135 [00:06<00:08, 12.86it/s] 21%|βββ | 29/135 [00:06<00:08, 12.28it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 21%|βββ | 29/135 [00:06<00:08, 12.28it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 21%|βββ | 29/135 [00:06<00:08, 12.28it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 21%|βββ | 29/135 [00:06<00:08, 12.28it/s] 24%|βββ | 32/135 [00:06<00:06, 14.78it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.weight[0m", shape: (2048,), dtype: float16 24%|βββ | 32/135 [00:06<00:06, 14.78it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 24%|βββ | 32/135 [00:06<00:06, 14.78it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 24%|βββ | 32/135 [00:07<00:06, 14.78it/s] 26%|βββ | 35/135 [00:07<00:07, 12.60it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 26%|βββ | 35/135 [00:07<00:07, 12.60it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 26%|βββ | 35/135 [00:07<00:07, 12.60it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 26%|βββ | 35/135 [00:07<00:07, 12.60it/s] 28%|βββ | 38/135 [00:07<00:06, 15.07it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.weight[0m", shape: (2048,), dtype: float16 28%|βββ | 38/135 [00:07<00:06, 15.07it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 28%|βββ | 38/135 [00:07<00:06, 15.07it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 28%|βββ | 38/135 [00:07<00:06, 15.07it/s] 30%|βββ | 41/135 [00:07<00:07, 13.33it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 30%|βββ | 41/135 [00:07<00:07, 13.33it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 30%|βββ | 41/135 [00:07<00:07, 13.33it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 30%|βββ | 41/135 [00:07<00:07, 13.33it/s] 33%|ββββ | 44/135 [00:07<00:05, 15.58it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.weight[0m", shape: (2048,), dtype: float16 33%|ββββ | 44/135 [00:07<00:05, 15.58it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 33%|ββββ | 44/135 [00:07<00:05, 15.58it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 33%|ββββ | 44/135 [00:07<00:05, 15.58it/s] 35%|ββββ | 47/135 [00:08<00:06, 13.02it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 35%|ββββ | 47/135 [00:08<00:06, 13.02it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 35%|ββββ | 47/135 [00:08<00:06, 13.02it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 35%|ββββ | 47/135 [00:08<00:06, 13.02it/s] 37%|ββββ | 50/135 [00:08<00:05, 15.39it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.weight[0m", shape: (2048,), dtype: float16 37%|ββββ | 50/135 [00:08<00:05, 15.39it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 37%|ββββ | 50/135 [00:08<00:05, 15.39it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 37%|ββββ | 50/135 [00:08<00:05, 15.39it/s] 39%|ββββ | 53/135 [00:08<00:05, 13.68it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 39%|ββββ | 53/135 [00:08<00:05, 13.68it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 39%|ββββ | 53/135 [00:08<00:05, 13.68it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 39%|ββββ | 53/135 [00:08<00:05, 13.68it/s] 41%|βββββ | 56/135 [00:08<00:04, 15.94it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.weight[0m", shape: (2048,), dtype: float16 41%|βββββ | 56/135 [00:08<00:04, 15.94it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 41%|βββββ | 56/135 [00:08<00:04, 15.94it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 41%|βββββ | 56/135 [00:08<00:04, 15.94it/s] 44%|βββββ | 59/135 [00:08<00:05, 13.32it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 44%|βββββ | 59/135 [00:08<00:05, 13.32it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 44%|βββββ | 59/135 [00:08<00:05, 13.32it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 44%|βββββ | 59/135 [00:08<00:05, 13.32it/s] 46%|βββββ | 62/135 [00:08<00:04, 15.85it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.weight[0m", shape: (2048,), dtype: float16 46%|βββββ | 62/135 [00:08<00:04, 15.85it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 46%|βββββ | 62/135 [00:08<00:04, 15.85it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 46%|βββββ | 62/135 [00:09<00:04, 15.85it/s] 48%|βββββ | 65/135 [00:09<00:05, 13.89it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 48%|βββββ | 65/135 [00:09<00:05, 13.89it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 48%|βββββ | 65/135 [00:09<00:05, 13.89it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 48%|βββββ | 65/135 [00:09<00:05, 13.89it/s] 50%|βββββ | 68/135 [00:09<00:04, 16.19it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.weight[0m", shape: (2048,), dtype: float16 50%|βββββ | 68/135 [00:09<00:04, 16.19it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 50%|βββββ | 68/135 [00:09<00:04, 16.19it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 50%|βββββ | 68/135 [00:09<00:04, 16.19it/s] 53%|ββββββ | 71/135 [00:09<00:04, 13.33it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 53%|ββββββ | 71/135 [00:09<00:04, 13.33it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 53%|ββββββ | 71/135 [00:09<00:04, 13.33it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 53%|ββββββ | 71/135 [00:09<00:04, 13.33it/s] 55%|ββββββ | 74/135 [00:09<00:03, 15.75it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.weight[0m", shape: (2048,), dtype: float16 55%|ββββββ | 74/135 [00:09<00:03, 15.75it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 55%|ββββββ | 74/135 [00:09<00:03, 15.75it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 55%|ββββββ | 74/135 [00:09<00:03, 15.75it/s] 57%|ββββββ | 77/135 [00:10<00:04, 13.94it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 57%|ββββββ | 77/135 [00:10<00:04, 13.94it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 57%|ββββββ | 77/135 [00:10<00:04, 13.94it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 57%|ββββββ | 77/135 [00:10<00:04, 13.94it/s] 59%|ββββββ | 80/135 [00:10<00:03, 16.18it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.weight[0m", shape: (2048,), dtype: float16 59%|ββββββ | 80/135 [00:10<00:03, 16.18it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 59%|ββββββ | 80/135 [00:10<00:03, 16.18it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 59%|ββββββ | 80/135 [00:10<00:03, 16.18it/s] 61%|βββββββ | 83/135 [00:10<00:03, 13.47it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 61%|βββββββ | 83/135 [00:10<00:03, 13.47it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 61%|βββββββ | 83/135 [00:10<00:03, 13.47it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 61%|βββββββ | 83/135 [00:10<00:03, 13.47it/s] 64%|βββββββ | 86/135 [00:10<00:03, 15.99it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.weight[0m", shape: (2048,), dtype: float16 64%|βββββββ | 86/135 [00:10<00:03, 15.99it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 64%|βββββββ | 86/135 [00:10<00:03, 15.99it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 64%|βββββββ | 86/135 [00:10<00:03, 15.99it/s] 66%|βββββββ | 89/135 [00:10<00:03, 13.88it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 66%|βββββββ | 89/135 [00:10<00:03, 13.88it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 66%|βββββββ | 89/135 [00:10<00:03, 13.88it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 66%|βββββββ | 89/135 [00:10<00:03, 13.88it/s] 68%|βββββββ | 92/135 [00:10<00:02, 16.18it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.weight[0m", shape: (2048,), dtype: float16 68%|βββββββ | 92/135 [00:10<00:02, 16.18it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 68%|βββββββ | 92/135 [00:10<00:02, 16.18it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 68%|βββββββ | 92/135 [00:11<00:02, 16.18it/s] 70%|βββββββ | 95/135 [00:11<00:02, 13.39it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 70%|βββββββ | 95/135 [00:11<00:02, 13.39it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 70%|βββββββ | 95/135 [00:11<00:02, 13.39it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 70%|βββββββ | 95/135 [00:11<00:02, 13.39it/s] 73%|ββββββββ | 98/135 [00:11<00:02, 15.88it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.weight[0m", shape: (2048,), dtype: float16 73%|ββββββββ | 98/135 [00:11<00:02, 15.88it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 73%|ββββββββ | 98/135 [00:11<00:02, 15.88it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 73%|ββββββββ | 98/135 [00:11<00:02, 15.88it/s] 75%|ββββββββ | 101/135 [00:11<00:02, 14.11it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 75%|ββββββββ | 101/135 [00:11<00:02, 14.11it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 75%|ββββββββ | 101/135 [00:11<00:02, 14.11it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 75%|ββββββββ | 101/135 [00:11<00:02, 14.11it/s] 77%|ββββββββ | 104/135 [00:11<00:01, 16.40it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.weight[0m", shape: (2048,), dtype: float16 77%|ββββββββ | 104/135 [00:11<00:01, 16.40it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 77%|ββββββββ | 104/135 [00:11<00:01, 16.40it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 77%|ββββββββ | 104/135 [00:11<00:01, 16.40it/s] 79%|ββββββββ | 107/135 [00:12<00:02, 13.62it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 79%|ββββββββ | 107/135 [00:12<00:02, 13.62it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 79%|ββββββββ | 107/135 [00:12<00:02, 13.62it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 79%|ββββββββ | 107/135 [00:12<00:02, 13.62it/s] 81%|βββββββββ | 110/135 [00:12<00:01, 16.17it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.weight[0m", shape: (2048,), dtype: float16 81%|βββββββββ | 110/135 [00:12<00:01, 16.17it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 81%|βββββββββ | 110/135 [00:12<00:01, 16.17it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 81%|βββββββββ | 110/135 [00:12<00:01, 16.17it/s] 84%|βββββββββ | 113/135 [00:12<00:01, 14.29it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 84%|βββββββββ | 113/135 [00:12<00:01, 14.29it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 84%|βββββββββ | 113/135 [00:12<00:01, 14.29it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 84%|βββββββββ | 113/135 [00:12<00:01, 14.29it/s] 86%|βββββββββ | 116/135 [00:12<00:01, 16.64it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.weight[0m", shape: (2048,), dtype: float16 86%|βββββββββ | 116/135 [00:12<00:01, 16.64it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 86%|βββββββββ | 116/135 [00:12<00:01, 16.64it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 86%|βββββββββ | 116/135 [00:12<00:01, 16.64it/s] 88%|βββββββββ | 119/135 [00:12<00:01, 13.75it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 88%|βββββββββ | 119/135 [00:12<00:01, 13.75it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 88%|βββββββββ | 119/135 [00:12<00:01, 13.75it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 88%|βββββββββ | 119/135 [00:12<00:01, 13.75it/s] 90%|βββββββββ | 122/135 [00:12<00:00, 16.30it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.weight[0m", shape: (2048,), dtype: float16 90%|βββββββββ | 122/135 [00:12<00:00, 16.30it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 90%|βββββββββ | 122/135 [00:12<00:00, 16.30it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 90%|βββββββββ | 122/135 [00:13<00:00, 16.30it/s] 93%|ββββββββββ| 125/135 [00:13<00:00, 14.36it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 93%|ββββββββββ| 125/135 [00:13<00:00, 14.36it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 93%|ββββββββββ| 125/135 [00:13<00:00, 14.36it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 93%|ββββββββββ| 125/135 [00:13<00:00, 14.36it/s] 95%|ββββββββββ| 128/135 [00:13<00:00, 16.75it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.weight[0m", shape: (2048,), dtype: float16 95%|ββββββββββ| 128/135 [00:13<00:00, 16.75it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 95%|ββββββββββ| 128/135 [00:13<00:00, 16.75it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 95%|ββββββββββ| 128/135 [00:13<00:00, 16.75it/s] 97%|ββββββββββ| 131/135 [00:13<00:00, 13.76it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 97%|ββββββββββ| 131/135 [00:13<00:00, 13.76it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 97%|ββββββββββ| 131/135 [00:13<00:00, 13.76it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 97%|ββββββββββ| 131/135 [00:13<00:00, 13.76it/s] 99%|ββββββββββ| 134/135 [00:13<00:00, 16.33it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.norm.weight[0m", shape: (2048,), dtype: float16 99%|ββββββββββ| 134/135 [00:13<00:00, 16.33it/s] 100%|ββββββββββ| 135/135 [00:13<00:00, 9.82it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:197: Unloading HF weight file: /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors [2024-06-04 20:08:50] INFO stats.py:77: [92mTime usage[0m: HF loading: 3.678 sec; Pre-quantization mapping: 4.070 sec; Quantization: 0.000 sec [2024-06-04 20:08:50] INFO stats.py:91: [92mRAM usage[0m: Peak RAM: 4.098 GB. Total bytes loaded from disk: 4.098 GB [2024-06-04 20:08:50] INFO convert_weight.py:155: [92mParameter size[0m after quantization: 2.049 GB [2024-06-04 20:08:50] INFO convert_weight.py:160: [92mTotal parameters[0m: 1,100,048,384 [2024-06-04 20:08:50] INFO convert_weight.py:161: [92mBits per parameter[0m: 16.000 [2024-06-04 20:08:50] INFO convert_weight.py:166: Saved to directory: [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC[0m All finished, 58 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/ndarray-cache.json |