Vicuna v1.5 Has Been Released!
Shoutout to [email protected] for catching this in an earlier post.
Given Vicuna was a widely appreciated member of the original Llama series, it’ll be exciting to see this model evolve and adapt with fresh datasets and new training and fine-tuning approaches.
Feel free using this megathread to chat about Vicuna and any of your experiences with Vicuna v1.5!
Starting off with Vicuna v1.5
TheBloke is already sharing models!
Vicuna v1.5 GPTQ
7B
13B
Vicuna Model Card
Model Details
Vicuna is a chat assistant fine-tuned from 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: https://github.com/lm-sys/FastChat
- Blog: https://lmsys.org/blog/2023-03-30-vicuna/
- Paper: https://arxiv.org/abs/2306.05685
- Demo: https://chat.lmsys.org/
Uses
The primary use of Vicuna is for research on large language models and chatbots. The target userbase includes researchers and hobbyists interested in natural language processing, machine learning, and artificial intelligence.
How to Get Started with the Model
- Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights
- APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api
Training Details
Vicuna v1.5 is fine-tuned from Llama 2 using supervised instruction. The model was trained on approximately 125K conversations from ShareGPT.com.
For additional details, please refer to the “Training Details of Vicuna Models” section in the appendix of the linked paper.
Evaluation Results
Vicuna is evaluated using standard benchmarks, human preferences, and LLM-as-a-judge. For more detailed results, please refer to the paper and leaderboard.
Pretty nice. Is the demo on Vicuna 1.5 right now? There doesn’t seem to be any tag so I’m not sure if it’s v1 or v1.5, they also still link to the old blog post when you click on Vicuna there.
Not 100% sure about the demo without clear tagging, but it appears officially out on huggingface so I’m sure we’ll have plenty of other demonstrations hit the web soon (if not this one).
This is all pretty fresh so I’m sure the missing tag denoting v1.5 it was just a small oversight from whoever manages the tool.
Very curious to see more benchmarks and user feedback though! A lot of people liked Vicuna. Let us know your experiences if you get a chance to interact with the model.
