Upload folder using huggingface_hub

README.md

@@ -0,0 +1,48 @@
+
+## llama2.c-stories15M-pruned50
+This repo contains model files for [llama2.c 15M tinystories](https://huggingface.co/Xenova/llama2.c-stories15M) optimized for [NM-vLLM](https://github.com/neuralmagic/nm-vllm), a high-throughput serving engine for compressed LLMs.
+
+This model was pruned with [SparseGPT](https://arxiv.org/abs/2301.00774), using [llm-compressor](https://github.com/vllm-project/llm-compressor).
+
+
+## Sparsification
+
+Install [llm-compressor](https://github.com/vllm-project/llm-compressor):
+```bash
+pip install llmcompressor
+```
+
+```python
+from llmcompressor.transformers import oneshot
+from llmcompressor.transformers import SparseAutoModelForCausalLM
+
+hf_model_stub = "Xenova/llama2.c-stories15M"
+calibration_dataset = "open_platypus"
+output_directory = f"{hf_model_stub.split('/')[-1]}-pruned_50.2of4-uncompressed"
+
+model = SparseAutoModelForCausalLM.from_pretrained(hf_model_stub, torch_dtype="auto", device_map="auto")
+
+recipe = """
+test_stage:
+  obcq_modifiers:
+    SparseGPTModifier:
+      sparsity: 0.5
+      sequential_update: true
+      mask_structure: "2:4"
+      targets: ['re:model.layers.\d*$']
+"""
+
+
+oneshot(
+    model=model,
+    dataset=calibration_dataset,
+    recipe=recipe,
+    output_dir=output_directory,
+)
+
+model.save_pretrained(output_directory, save_compressed=False)
+```
+
+## Slack
+
+For further support, and discussions on these models and AI in general, join [Neural Magic's Slack Community](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ)

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "/home/rahul/.cache/huggingface/hub/models--Xenova--llama2.c-stories15M/snapshots/ccdd47c2dc554aeecd2bb4e713e1c988f206a296",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 48,
+  "hidden_act": "silu",
+  "hidden_size": 288,
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "max_position_embeddings": 256,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 6,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "quant_method": "compressed-tensors",
+    "sparsity_config": {
+      "format": "dense",
+      "global_sparsity": 0.12233772669884009,
+      "ignore": [
+        "lm_head"
+      ],
+      "registry_requires_subclass": false,
+      "sparsity_structure": "2:4",
+      "targets": [
+        "Linear"
+      ]
+    },
+    "version": "0.7.1"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3933ab3ff3e2a8c73a21e12402edbb4d1fa6b4e4a424f52d9481ccb9cfb3ae78
+size 60772936

recipe.yaml

@@ -0,0 +1,7 @@
+test_stage:
+  obcq_modifiers:
+    SparseGPTModifier:
+      sparsity: 0.5
+      sequential_update: true
+      mask_structure: '2:4'
+      targets: ['re:model.layers.\d*$']

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}