Intel/GLM-5-int4-mixed-AutoRound

Model Details

This model is a mixed int4 model with group_size 64 and symmetric 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.

Some users have reported unexpected outputs with this model. Please use it with caution for now. We will try to investigate the root cause and release an updated version later.

vllm inference

Setup

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

MTP is supported.

CUDA_VISIBLE_DEVICES=0,1,2,3 vllm serve  Intel/GLM-5-int4-mixed-AutoRound  \
     --tensor-parallel-size 4 \
     --gpu-memory-utilization 0.85 \
     --tool-call-parser glm47 \
     --reasoning-parser glm45 \
     --enable-auto-tool-choice \
     --speculative-config.method mtp \
     --speculative-config.num_speculative_tokens 1 \
     --served-model-name glm-5

curl http://localhost:8009/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 AutoRound in one sentence."}
    ],
    "max_tokens": 512
  } '

Generate the Model

auto_round /storage/wenhuach/GLM-5/ --iters 0 --disable_opt_rtn --ignore_layers layers.0,layers.1,layers.2,self_attn,shared_experts,eh_proj  --output_dir /GLM-5-int4  --group_size 64

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