初始化项目，由ModelHub XC社区提供模型

Model: espressor/meta-llama.Llama-3.2-3B-Instruct_W4A16
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+datasets:
+- HuggingFaceH4/ultrachat_200k
+base_model:
+- meta-llama/Llama-3.2-3B-Instruct
+library_name: transformers
+---
+
+## meta-llama/Llama-3.2-3B-Instruct - W4A16 Compression
+
+This is a compressed model using [llmcompressor](https://github.com/vllm-project/llm-compressor).
+
+## Compression Configuration
+
+- Base Model: meta-llama/Llama-3.2-3B-Instruct
+- Compression Scheme: W4A16
+- Dataset: HuggingFaceH4/ultrachat_200k
+- Dataset Split: train_sft
+- Number of Samples: 512
+- Preprocessor: chat
+- Maximum Sequence Length: 131072
+
+## Sample Output
+
+#### Prompt: 
+
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+Cutting Knowledge Date: December 2023
+Today Date: 28 Nov 2024
+
+<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+Who is Alan Turing?<|eot_id|>
+```
+
+#### Output: 
+
+```
+<|begin_of_text|><|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+Cutting Knowledge Date: December 2023
+Today Date: 28 Nov 2024
+
+<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+Who is Alan Turing?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+Alan Turing (1912-1954) was a British mathematician, computer scientist, logician, and philosopher who made significant contributions to the development of computer science, artificial intelligence, and cryptography. He is widely considered one of the most influential figures in the history of computer science.
+
+Early Life and Education:
+
+Turing was born in London, England, on June 23, 1912. He was educated at King's School in Croton, and later at King's College, Cambridge, where he studied mathematics and philosophy. During World War II, Turing worked at the Government Code and Cypher School (GC
+```
+
+## Evaluation
+
+<TODO>
+

config.json

@@ -0,0 +1,79 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 128,
+          "num_bits": 4,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": 1.8892119940814551,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {
+      "format": "dense",
+      "global_sparsity": 0.12753888440168046,
+      "ignore": [],
+      "registry_requires_subclass": false,
+      "sparsity_structure": "unstructured",
+      "targets": []
+    }
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cfc201dbd264275b74664a0974d8a67e517640fe885c4eef12fd60f68182619
+size 3029762904

recipe.yaml

@@ -0,0 +1,6 @@
+DEFAULT_stage:
+  DEFAULT_modifiers:
+    GPTQModifier:
+      targets: Linear
+      ignore: [lm_head]
+      scheme: W4A16

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}