Intel/GLM-5-int4-mixed-AutoRound

Model Details

This model is a mixed int4 model with group_size 128 and asymmetric quantization of zai-org/GLM-5 generated by intel/auto-round. Please follow the license of the original model.

The model is quantized with pure RTN mode

vllm inference

Setup

pip install git+https://github.com/vllm-project/vllm.git@main


pip install git+https://github.com/huggingface/transformers.git

MTP has not been supported, we will try to fix it later.

CUDA_VISIBLE_DEVICES=1,2,3,4 vllm serve  /xuehaosu/glm5_whc/GLM-5-w4g128/  \
     --tensor-parallel-size 4 \
     --gpu-memory-utilization 0.85 \
     --tool-call-parser glm47 \
     --reasoning-parser glm45 \
     --enable-auto-tool-choice \
     --served-model-name glm-5

curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d ' {
    "model": "glm-5",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Summarize GLM-5 in one sentence."}
    ],
    "temperature": 1,
    "max_tokens": 4096
  } '

Generate the Model

this pr is required https://github.com/intel/auto-round/pull/1466

auto-round zai-org/GLM-5 --ignore_layers layers.0,layers.1,layers.2,self_attn,shared_experts --iters 0 --disable_opt_rtn --output_dir ./glm5_int4 --format auto_round:auto_awq --asym

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