Vicuna is a chat assistant trained by
LMSYS. This is a 4-bit AWQ quantized Vicuna v1.3 model.
AWQ is an
efficient and accurate low-bit weight quantization (INT3/4) for LLMs, supporting instruction-tuned models and multi-modal LMs.
If you find AWQ useful or relevant to your research, please kindly cite the paper:
1@article{lin2023awq,
2 title={AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration},
3 author={Lin, Ji and Tang, Jiaming and Tang, Haotian and Yang, Shang and Dang, Xingyu and Han, Song},
4 journal={arXiv},
5 year={2023}
6}
Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
