Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Qualityhttps://vicuna.lmsys.org/
Vicuna-13B is an open-source chatbot based on a fine-tuned LLaMA base model trained on user-shared conversations collected from ShareGPT.com. The enhanced dataset and easy-to-use, scalable infrastructure of Vicuna-13B provide a competitive performance compared to other open-source models like Stanford Alpaca, as demonstrated in a preliminary evaluation. The training scripts were enhanced to handle multi-round conversations and long sequences, and the training was done with PyTorch FSDP on 8 A100 GPUs in one day. A lightweight distributed serving system was implemented for the demo. The model quality was evaluated using a set of 80 diverse questions and GPT-4 to judge the model outputs by combining the outputs from each model into a single prompt for each question. The post invites the community to interact with the online demo to test the chatbot's capabilities.