Does it or will it support Vicuna-13b-v1.1 finetuning?

Open ghost opened this issue 2 years ago • 1 comments

Thanks for creating such an amazing project.

Vicuna-13b-v1.1 seems to achieve impressive performance in tasks in multiple languages. I believe it would be a good idea to conduct further fine-tuning based on it. So, will this project support Vicuna-13b-v1.1 finetuning later?

Apr 19 '23 08:04 ghost

Hi, Thank you very much for your interest in our work. We will support vicuna-13b-v1.1 very soon.

Apr 19 '23 14:04 shizhediao

Hi, The vicuna model can be finetuned by directly changing the --model_name_or_path. If you encounter any issues, please create a new issue and let us know. Thanks!

Jun 19 '23 11:06 shizhediao