--- license: apache-2.0 datasets: - NeelNanda/pile-10k language: - en --- ## Model Details This model is an int2 model with group_size 32 of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) generated by [intel/auto-round](https://github.com/intel/auto-round). The model size of it is 2.6 Gb. Inference of this model is compatible with AutoGPTQ's Kernel. ### Reproduce the model Here is the sample command to reproduce the model ```bash 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 32 \ --bits 2 \ --nsamples 512 \ --iters 200 \ --minmax_lr 0.01 \ --deployment_device 'auto_round' \ --output_dir "./tmp_autoround" \ ``` ### Evaluate the model Install [lm-eval-harness 0.4.2](https://github.com/EleutherAI/lm-evaluation-harness.git) from source. ```bash git clone https://github.com/intel/auto-round cd auto-round/examples/language-modeling pip install -r requirements.txt python3 eval_042/evaluation.py --model_name ./tmp_autoround --eval_bs 16 --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,mmlu ``` | Metric | FP16 | INT2 | | -------------- | ------ | ------ | | Avg. | 0.6591 | 0.6014 | | mmlu | 0.5877 | 0.5140 | | lambada_openai | 0.7155 | 0.6295 | | hellaswag | 0.6602 | 0.5856 | | winogrande | 0.7411 | 0.6835 | | piqa | 0.8014 | 0.7748 | | truthfulqa_mc1 | 0.5251 | 0.4651 | | openbookqa | 0.3520 | 0.2900 | | boolq | 0.8529 | 0.8226 | | arc_easy | 0.8136 | 0.7647 | | arc_challenge | 0.5418 | 0.4846 | ## 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](https://github.com/intel/neural-compressor) * Intel Extension for Transformers [link](https://github.com/intel/intel-extension-for-transformers) ## 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](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)