INCModel2/DeepSeek-R1-MXFP4-CT-AutoRound

Model Details

This model card is for mxfp4 quantization of unsloth/DeepSeek-R1-BF16 based on intel/auto-round saved in llm_compressor format. Please follow the license of the original model.

How to Use

The step-by-step README of quantization and evaluation can be found in Intel Neural Compressor Examples.

Evaluate

# auto-round 0.14.2
# vllm 0.26.1rc1.dev451+gb1e12d142

export CUDA_VISIBLE_DEVICES=4,5,6,7
export VLLM_QDQ=1
python vllm/examples/basic/offline_inference/generate.py \
        --model /software/data/jenkins/saved_models/DeepSeek-R1_mxfp4_LLMC/DeepSeek-R1-BF16-mxfp-w4g32/ \
        --max-model-len 2048 \
        -tp 4 \
        --enforce-eager \
        --gpu-memory-utilization 0.9

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.