commit b270f56c021283c7817b2db978912bdd9311c852 Author: ModelHub XC Date: Thu Oct 22 23:46:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/Qwen2.5-32B-quantized.w8a16 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..be422e9 --- /dev/null +++ b/README.md @@ -0,0 +1,177 @@ +--- +tags: +- int8 +- vllm +- llm-compressor +language: +- en +pipeline_tag: text-generation +license: apache-2.0 +base_model: +- Qwen/Qwen2.5-32B +--- + +# Qwen2.5-32B-quantized.w8a16 + +## Model Overview +- **Model Architecture:** Qwen2 + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Weight quantization:** INT8 +- **Intended Use Cases:** Similarly to [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B), this is a base language model. +- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). +- **Release Date:** 10/09/2024 +- **Version:** 1.0 +- **Model Developers:** Neural Magic + +Quantized version of [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B). +It achieves an OpenLLMv1 score of 75.4, compared to 75.3 for [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B). + +### Model Optimizations + +This model was obtained by quantizing the weights of [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) to INT8 data type. +This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%. + +Only the weights of the linear operators within transformers blocks are quantized. +Symmetric per-channel quantization is applied, in which a linear scaling per output dimension maps the INT8 and floating point representations of the quantized weights. +The [GPTQ](https://arxiv.org/abs/2210.17323) algorithm is applied for quantization, as implemented in the [llm-compressor](https://github.com/vllm-project/llm-compressor) library. + + +## Deployment + +This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below. + +```python +from vllm import LLM, SamplingParams +from transformers import AutoTokenizer + +model_id = "neuralmagic/Qwen2.5-32B-quantized.w8a16" +number_gpus = 1 +max_model_len = 8192 + +sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256) + +tokenizer = AutoTokenizer.from_pretrained(model_id) + +prompt = "Give me a short introduction to large language model." + +llm = LLM(model=model_id, tensor_parallel_size=number_gpus, max_model_len=max_model_len) + +outputs = llm.generate(prompt, sampling_params) + +generated_text = outputs[0].outputs[0].text +print(generated_text) +``` + +vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. + + + +## Evaluation + +The model was evaluated on the OpenLLMv1 benchmark, composed of MMLU, ARC-Challenge, GSM-8K, Hellaswag, Winogrande and TruthfulQA. +Evaluation was conducted using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) and the [vLLM](https://docs.vllm.ai/en/stable/) engine. + +### Accuracy + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Category + Benchmark + Qwen2.5-32B + Qwen2.5-32B-quantized.w8a16
(this model) + 		Recovery +
OpenLLM v1 +
MMLU (5-shot) + 83.25 + 83.19 + 99.9% +
ARC Challenge (25-shot) + 66.30 + 66.04 + 99.6% +
GSM-8k (5-shot, strict-match) + 78.09 + 78.62 + 100.7% +
Hellaswag (10-shot) + 85.08 + 85.14 + 100.1% +
Winogrande (5-shot) + 81.29 + 81.61 + 100.4% +
TruthfulQA (0-shot, mc2) + 57.76 + 57.78 + 100.0% +
Average + 75.30 + 75.40 + 100.1% +
+ +### Reproduction + +The results were obtained using the following command: + +``` +lm_eval \ + --model vllm \ + --model_args pretrained="neuralmagic/Qwen2.5-32B-quantized.w8a16",dtype=auto,max_model_len=4096,add_bos_token=True,tensor_parallel_size=1 \ + --tasks openllm \ + --batch_size auto +``` diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..0bf0067 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e5fe122cee129f42b66da0fb41770ecd270f32a61b2def018b5d772786522ce +size 1609 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..59ff6e5 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "bos_token_id": 151643, + "eos_token_id": 151643, + "max_new_tokens": 2048, + "transformers_version": "4.45.1" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00007.safetensors b/model-00001-of-00007.safetensors new file mode 100644 index 0000000..864a163 --- /dev/null +++ b/model-00001-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e3a8306c949b7bd00efd56ce6ebfe5109ded16f1b6013985ba434f2d7e07155 +size 4997768688 diff --git a/model-00002-of-00007.safetensors b/model-00002-of-00007.safetensors new file mode 100644 index 0000000..f03020a --- /dev/null +++ b/model-00002-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2944b9120047839ebc7f4e1671e2108e4404046ef85f53e4185ec31b5476fc55 +size 4914431192 diff --git a/model-00003-of-00007.safetensors b/model-00003-of-00007.safetensors new file mode 100644 index 0000000..77d8e2e --- /dev/null +++ b/model-00003-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3097f1aa3e91d9cb084a403a8db0352b1cdd4438b0c38734faeb95ebe90d776 +size 4877711368 diff --git a/model-00004-of-00007.safetensors b/model-00004-of-00007.safetensors new file mode 100644 index 0000000..66514b8 --- /dev/null +++ b/model-00004-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e707734533fb52be1da3916f1bba75f99d5dab28d1ef425e6235a4ad6bd802c2 +size 4877711368 diff --git a/model-00005-of-00007.safetensors b/model-00005-of-00007.safetensors new file mode 100644 index 0000000..e37eae9 --- /dev/null +++ b/model-00005-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:400891bb17900f7acdf9e0953f73aac1209888e6af0e54f8e26aa8e8476c85f6 +size 4877711368 diff --git a/model-00006-of-00007.safetensors b/model-00006-of-00007.safetensors new file mode 100644 index 0000000..03dc3ef --- /dev/null +++ b/model-00006-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf00e1dc1ddf3180040b0d9c8b7be317f6b4febb120bb54187cd8b4ff953d004 +size 4877711368 diff --git a/model-00007-of-00007.safetensors b/model-00007-of-00007.safetensors new file mode 100644 index 0000000..77a64b8 --- /dev/null +++ b/model-00007-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:297a42991bc59bb87861a349de5b08be978e21d5b3255f931fec67a261a66f63 +size 4908588368 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..55a04dc --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08cd62f5af35614b44090f404125d296e1e4e00ffab35d803f5ae46245a9c20d +size 144580 diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000..87d3359 --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,9 @@ +quant_stage: + quant_modifiers: + GPTQModifier: + sequential_update: true + dampening_frac: 0.1 + ignore: [lm_head] + scheme: W8A16 + targets: Linear + observer: mse diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..17305b3 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..33d22a4 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb73a25aba3c83c6c815a03a334b0440bd549f9a54fa3673e005f5532f6b32fe +size 11421995 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..acb1852 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cefaa66de8fae4a09ca18a9c3a7fd8b61311ed568e5f4e634f6a3d95a2a9e889 +size 7229 diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833