Intel/Mistral-7B-Instruct-v0.2-int4-inc

Model Details

This model is an int4 model with group_size 128 of mistralai/Mistral-7B-Instruct-v0.2 generated by intel/auto-round. Inference of this model is compatible with AutoGPTQ's Kernel.

Reproduce the model

Here is the sample command to reproduce the model

git clone https://github.com/intel/auto-round
cd auto-round/examples/language-modeling
pip install -r requirements.txt
python3 main.py \
--model_name  mistralai/Mistral-7B-Instruct-v0.2 \
--device 0 \
--group_size 128 \
--bits 4 \
--iters 1000 \
--deployment_device 'gpu' \
--output_dir "./tmp_autoround" \

Evaluate the model

Install lm-eval-harness 0.4.2 from source.

lm_eval --model hf --model_args pretrained="Intel/Mistral-7B-Instruct-v0.2-int4-inc",autogptq=True,gptq_use_triton=True --device cuda:0 --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,rte,arc_easy,arc_challenge,mmlu --batch_size 32

Metric	FP16	INT4
Avg.	0.6591	0.6573
mmlu	0.5877	0.5866
lambada_openai	0.7155	0.7089
hellaswag	0.6602	0.6567
winogrande	0.7411	0.7395
piqa	0.8014	0.8074
truthfulqa_mc1	0.5251	0.5116
openbookqa	0.3520	0.3420
boolq	0.8529	0.8526
arc_easy	0.8136	0.8144
arc_challenge	0.5418	0.5538

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 link
• Intel Extension for Transformers link

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}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }

arxiv github