Intel/Wan2.2-T2V-A14B-Diffusers-int4-AutoRound

Model Details

This model is an int4 model with group_size 128 and symmetric quantization of Wan-AI/Wan2.2-T2V-A14B-Diffusers generated by intel/auto-round. Please follow the license of the original model.

How to Use

Environment

pip install pip install git+https://github.com/lvliang-intel/vllm-omni.git@feats/ar-w4a16-wan22
pip install transformers

VLLM Usage

Serving:

vllm serve Intel/Wan2.2-T2V-A14B-Diffusers-int4-AutoRound --omni --port 8091

Access the service:

curl -X POST "http://127.0.0.1:8091/v1/videos/sync" \
  -F 'prompt=Cherry blossoms swaying gently in the breeze, petals falling, cinematic motion' \
  -F 'negative_prompt=blur, low quality, distortion, artifacts' \
  -F 'width=832' \
  -F 'height=480' \
  -F 'num_frames=48' \
  -F 'fps=16' \
  -F 'num_inference_steps=40' \
  -F 'guidance_scale=5.0' \
  -F 'guidance_scale_2=6.0' \
  -F 'boundary_ratio=0.875' \
  -F 'flow_shift=12.0' \
  --output t2v_output.mp4

Generate the Model

auto-round --model_name Wan-AI/Wan2.2-T2V-A14B-Diffusers --format auto_round --scheme W4A16 --iters 100 --nsamples 32 --batch-size 1 --num-inference-steps 3  --guidance-scale 5.0  --dataset coco2014 --output_dir Wan2.2-T2V-A14B-Diffusers-int4-AutoRound

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
• AutoRound

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