Vicuna Model Card
Model Details
Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.
- Developed by: LMSYS
- Model type: An auto-regressive language model based on the transformer architecture
- License: Llama 2 Community License Agreement
- Finetuned from model: Llama 2
Model Sources
- Repository: GitHub - lm-sys/FastChat: An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
- Blog: Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality | LMSYS Org
- Paper: [2306.05685] Judging LLM-as-a-judge with MT-Bench and Chatbot Arena
- Demo: https://chat.lmsys.org/
Uses
The primary use of Vicuna is research on large language models and chatbots. The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
How to Get Started with the Model
- Command line interface: GitHub - lm-sys/FastChat: An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
- APIs (OpenAI API, Huggingface API): GitHub - lm-sys/FastChat: An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Training Details
Vicuna v1.5 is fine-tuned from Llama 2 with supervised instruction fine-tuning. The training data is around 125K conversations collected from ShareGPT.com. See more details in the “Training Details of Vicuna Models” section in the appendix of this paper.
Evaluation
Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this paper and leaderboard.