commit 3077223b10df5534a39ba27d1dc5fb10680d0e6a Author: ModelHub XC Date: Fri Oct 23 22:04:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/QwQ-32B-Preview-FP8-dynamic 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..9fd5359 --- /dev/null +++ b/README.md @@ -0,0 +1,168 @@ +--- +tags: +- fp8 +- vllm +license: apache-2.0 +license_link: https://huggingface.co/Qwen/QwQ-32B-Preview/blob/main/LICENSE +language: + - en +base_model: Qwen/Qwen2.5-32B-Instruct +library_name: transformers +--- + +# QwQ-32B-Preview-FP8-dynamic + +## Model Overview +- **Model Architecture:** QwQ-32B-Preview + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Weight quantization:** FP8 + - **Activation quantization:** FP8 +- **Release Date:** 3/1/2025 +- **Version:** 1.0 +- **Model Developers:** Neural Magic + +Quantized version of [QwQ-32B-Preview](https://huggingface.co/Qwen/QwQ-32B-Preview). +It achieves an average score of 77.08 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 77.20. + +### Model Optimizations + +This model was obtained by quantizing the weights and activations of [QwQ-32B-Preview](https://huggingface.co/Qwen/QwQ-32B-Preview) to FP8 data type, ready for inference with vLLM >= 0.5.2. +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 and activations of the linear operators within transformers blocks are quantized. + +## Deployment + +### Use with vLLM + +This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below. + +```python +from transformers import AutoTokenizer +from vllm import LLM, SamplingParams + +max_model_len, tp_size = 4096, 1 +model_name = "neuralmagic-ent/QwQ-32B-Preview-FP8-dynamic" +tokenizer = AutoTokenizer.from_pretrained(model_name) +llm = LLM(model=model_name, tensor_parallel_size=tp_size, max_model_len=max_model_len, trust_remote_code=True) +sampling_params = SamplingParams(temperature=0.3, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id]) + +messages_list = [ + [{"role": "user", "content": "Who are you? Please respond in pirate speak!"}], +] + +prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list] + +outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params) + +generated_text = [output.outputs[0].text for output in outputs] +print(generated_text) +``` + +vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. + +## Creation + +This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below. + + +```python +import argparse +from transformers import AutoModelForCausalLM, AutoTokenizer +from llmcompressor.modifiers.quantization import QuantizationModifier +from llmcompressor.transformers import oneshot +import os + +def main(): + parser = argparse.ArgumentParser(description='Quantize a transformer model to FP8') + parser.add_argument('--model_id', type=str, required=True, + help='The model ID from HuggingFace (e.g., "meta-llama/Meta-Llama-3-8B-Instruct")') + parser.add_argument('--save_path', type=str, default='.', + help='Custom path to save the quantized model. If not provided, will use model_name-FP8-dynamic') + args = parser.parse_args() + + # Load model + model = AutoModelForCausalLM.from_pretrained( + args.model_id, device_map="auto", torch_dtype="auto", trust_remote_code=True, + ) + tokenizer = AutoTokenizer.from_pretrained(args.model_id) + + # Configure the quantization algorithm and scheme + recipe = QuantizationModifier( + targets="Linear", scheme="FP8_DYNAMIC", ignore=["lm_head"] + ) + + # Apply quantization + oneshot(model=model, recipe=recipe) + + save_path = os.path.join(args.save_path, args.model_id.split("/")[1] + "-FP8-dynamic") + os.makedirs(save_path, exist_ok=True) + + # Save to disk in compressed-tensors format + model.save_pretrained(save_path) + tokenizer.save_pretrained(save_path) + print(f"Model and tokenizer saved to: {save_path}") + +if __name__ == "__main__": + main() +``` + +## Evaluation + +The model was evaluated on OpenLLM Leaderboard [V1](https://huggingface.co/spaces/open-llm-leaderboard-old/open_llm_leaderboard) and [V2](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/), using the following commands: + +OpenLLM Leaderboard V1: +``` +lm_eval \ + --model vllm \ + --model_args pretrained="neuralmagic-ent/QwQ-32B-Preview-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \ + --tasks openllm \ + --write_out \ + --batch_size auto \ + --output_path output_dir \ + --show_config +``` + +OpenLLM Leaderboard V2: +``` +lm_eval \ + --model vllm \ + --model_args pretrained="neuralmagic-ent/QwQ-32B-Preview-FP8-dynamic",dtype=auto,add_bos_token=False,max_model_len=4096,tensor_parallel_size=1,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \ + --apply_chat_template \ + --fewshot_as_multiturn \ + --tasks leaderboard \ + --write_out \ + --batch_size auto \ + --output_path output_dir \ + --show_config + +``` + +### Accuracy + +#### OpenLLM Leaderboard V1 evaluation scores + +| Metric | Qwen/QwQ-32B-Preview | neuralmagic-ent/QwQ-32B-Preview-FP8-dynamic | +|-----------------------------------------|:---------------------------------:|:-------------------------------------------:| +| ARC-Challenge (Acc-Norm, 25-shot) | 70.73 | 71.08 | +| GSM8K (Strict-Match, 5-shot) | 83.09 | 82.18 | +| HellaSwag (Acc-Norm, 10-shot) | 85.77 | 85.88 | +| MMLU (Acc, 5-shot) | 82.67 | 82.67 | +| TruthfulQA (MC2, 0-shot) | 60.88 | 60.54 | +| Winogrande (Acc, 5-shot) | 80.03 | 80.11 | +| **Average Score** | **77.20** | **77.08** | +| **Recovery** | **100.00** | **99.84** | + +#### OpenLLM Leaderboard V2 evaluation scores + +| Metric | Qwen/QwQ-32B-Preview | neuralmagic-ent/QwQ-32B-Preview-FP8-dynamic | +|---------------------------------------------------------|:---------------------------------:|:-------------------------------------------:| +| IFEval (Inst-and-Prompt Level Strict Acc, 0-shot) | 42.34 | 40.48 | +| BBH (Acc-Norm, 3-shot) | 53.03 | 52.96 | +| Math-Hard (Exact-Match, 4-shot) | 21.15 | 20.82 | +| GPQA (Acc-Norm, 0-shot) | 2.97 | 1.99 | +| MUSR (Acc-Norm, 0-shot) | 9.57 | 10.93 | +| MMLU-Pro (Acc, 5-shot) | 52.00 | 51.62 | +| **Average Score** | **30.18** | **29.80** | +| **Recovery** | **100.00** | **98.74** | + 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..56c5e9b --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad1981c4c8f40f444b5e6348222a0d5e3fad39de0680e1f74582e3e5001e59fe +size 1801 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..d8ec693 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "4.46.2" +} 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..306cd4e --- /dev/null +++ b/model-00001-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbffc52dae3231d5a4557509bb51c96d668099c1cd62b88bb3e5c4d64f8056d8 +size 4997762744 diff --git a/model-00002-of-00007.safetensors b/model-00002-of-00007.safetensors new file mode 100644 index 0000000..4a8234b --- /dev/null +++ b/model-00002-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcc7259beaf742d18c8c852ffdbb5f4bb44f7f2cfcf4d7ca5766ba7de2ed8900 +size 4914421680 diff --git a/model-00003-of-00007.safetensors b/model-00003-of-00007.safetensors new file mode 100644 index 0000000..7d43a4d --- /dev/null +++ b/model-00003-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cc60d2c02b6483ea3925766520b864c9cd3aacacc81780a14de643176acb36b +size 4877702248 diff --git a/model-00004-of-00007.safetensors b/model-00004-of-00007.safetensors new file mode 100644 index 0000000..ac02e41 --- /dev/null +++ b/model-00004-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42d74595a0cbfdc89777b73902f555414a84f7b8cd4d55d40e2624c6cc4731c2 +size 4877702248 diff --git a/model-00005-of-00007.safetensors b/model-00005-of-00007.safetensors new file mode 100644 index 0000000..ec88872 --- /dev/null +++ b/model-00005-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:138cd6b5383f92247f7c07ccc80c7796e487c95d754157ab5e3257413acff970 +size 4877702248 diff --git a/model-00006-of-00007.safetensors b/model-00006-of-00007.safetensors new file mode 100644 index 0000000..174713e --- /dev/null +++ b/model-00006-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc98d930166e3f322fb0c7d3d6fab93255e7b9d6eb9dea8d4bbc1787a59dcd4a +size 4877702248 diff --git a/model-00007-of-00007.safetensors b/model-00007-of-00007.safetensors new file mode 100644 index 0000000..a1d4051 --- /dev/null +++ b/model-00007-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:329d13b64081bcbf80041d0a5faafda19ec0e0b8f3c9b344d8a8a66347859c70 +size 4908583200 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..0d02816 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecb9438a33bfc025000cd8575afc73dec022f58d448a1ac920cdbe1adca60e82 +size 102346 diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000..bf04f00 --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,6 @@ +DEFAULT_stage: + DEFAULT_modifiers: + QuantizationModifier: + ignore: [lm_head] + targets: [Linear] + scheme: FP8_DYNAMIC diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /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": "<|im_end|>", + "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..51ebb3b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa +size 11421896 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..ea31cfd --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e3278dffb14189645457aebd8f8426551a470264c7ac0dd0adfa6c9944f2088 +size 7383 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