Qwen2.5-Omni-7B-int4-AutoRound

Model Details

This model is a mixed int4 model with group_size 128 and symmetric quantization of Qwen/Qwen2.5-Omni-7B generated by intel/auto-round. Please follow the license of the original model.

vllm-omni inference

Setup

pip install git+https://github.com/lvliang-intel/vllm-omni.git@feats/ar-w4a16-qwen-omni
pip install git+https://github.com/huggingface/transformers.git

CUDA_VISIBLE_DEVICES=0 vllm serve Intel/Qwen2.5-Omni-7B-int4-AutoRound --omni --port 8091

curl -s http://localhost:8091/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Intel/Qwen2.5-Omni-7B-int4-AutoRound",
    "messages": [
      {
        "role": "system",
        "content": "You are Qwen, a virtual human developed by the Qwen Team, Alibaba Group, capable of perceiving auditory and visual inputs, as well as generating text and speech."
      },
      {
        "role": "user",
        "content": "What is 2 + 3? Answer with just the number."
      }
    ],
    "temperature": 0.0,
    "max_tokens": 2048,
    "repetition_penalty": 1.1
  }'

curl -s http://127.0.0.1:8091/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Intel/Qwen2.5-Omni-7B-int4-AutoRound",
    "messages": [
      {
        "role": "system",
        "content": "You are Qwen, a virtual human developed by the Qwen Team, Alibaba Group, capable of perceiving auditory and visual inputs, as well as generating text and speech."
      },
      {
        "role": "user",
        "content": [
          {
            "type": "image_url",
            "image_url": {
              "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Omni/demo/cars.jpg"
            }
          },
          {
            "type": "text",
            "text": "Describe this image in one short sentence."
          }
        ]
      }
    ],
    "temperature": 0.0,
    "max_tokens": 2048,
    "repetition_penalty": 1.1
  }'

curl -s http://127.0.0.1:8091/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Intel/Qwen2.5-Omni-7B-int4-AutoRound",
    "messages": [
      {
        "role": "system",
        "content": "You are Qwen, a virtual human developed by the Qwen Team, Alibaba Group, capable of perceiving auditory and visual inputs, as well as generating text and speech."
      },
      {
        "role": "user",
        "content": [
          {
            "type": "audio_url",
            "audio_url": {
              "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Omni/demo/cough.wav"
            }
          },
          {
            "type": "text",
            "text": "What sound can you hear? Answer in one short sentence."
          }
        ]
      }
    ],
    "temperature": 0.0,
    "max_tokens": 2048,
    "repetition_penalty": 1.1
  }'

Generate the Model

auto_round \
  --model Qwen/Qwen2.5-Omni-7B \
  --bits 4 \
  --group_size 128 \
  --format auto_round \
  --iters 200 \
  --lr 5e-3 \
  --output_dir tmp_qwen25_omni_w4a16 \
  --trust_remote_code

Ethical Considerations and Limitations

The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.

Therefore, before deploying any applications of the model, developers should perform safety testing.

Caveats and Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

Here are a couple of useful links to learn more about Intel's AI software:

• Intel Neural Compressor

Disclaimer

The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.

Cite

@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }

arxiv github