Model Details
This model is an int4 model with group_size 128 of meta-llama/Llama-2-7b-chat-hf 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 meta-llama/Llama-2-7b-chat-hf \
--device 0 \
--group_size 128 \
--bits 4 \
--nsamples 512 \
--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/Llama-2-7b-chat-hf-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. | 0.5797 | 0.5787 |
| mmlu | 0.4641 | 0.4620 |
| lambada_openai | 0.7101 | 0.7017 |
| hellaswag | 0.5779 | 0.5699 |
| winogrande | 0.6630 | 0.6592 |
| piqa | 0.7644 | 0.7661 |
| truthfulqa_mc1 | 0.3035 | 0.3146 |
| openbookqa | 0.3360 | 0.3340 |
| boolq | 0.7979 | 0.8064 |
| arc_easy | 0.7391 | 0.7336 |
| arc_challenge | 0.4411 | 0.4403 |
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:
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} }