GLM 5 int4 mixed AutoRound EU AI Act Compliance Profile

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

Your obligations as a GLM 5 int4 mixed AutoRound deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Base Model