đ Vicuna Model Card
Vicuna is an open - source chatbot. It's trained by fine - tuning LLaMA on user - shared conversations. This model is useful for research in large language models and chatbots, benefiting researchers and hobbyists in related fields.
đ Quick Start
No specific quick - start steps are provided in the original document.
⨠Features
- Vicuna is an auto - regressive language model based on the transformer architecture.
- It's trained on 70K conversations from ShareGPT.com.
- A set of 80 diverse questions and GPT - 4 are used for preliminary model quality evaluation.
đĻ Installation
No installation steps are provided in the original document.
đģ Usage Examples
No code examples are provided in the original document.
đ Documentation
Model Details
Property |
Details |
Model Type |
Vicuna is an open - source chatbot trained by fine - tuning LLaMA on user - shared conversations collected from ShareGPT. It is an auto - regressive language model, based on the transformer architecture. |
Model Date |
Vicuna was trained between March 2023 and April 2023. |
Organizations Developing the Model |
The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego. |
Paper or Resources for More Information |
https://vicuna.lmsys.org/ |
License |
Apache License 2.0 |
Where to Send Questions or Comments about the Model |
https://github.com/lm - sys/FastChat/issues |
Intended Use
Property |
Details |
Primary Intended Uses |
The primary use of Vicuna is research on large language models and chatbots. |
Primary Intended Users |
The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence. |
Training Dataset
70K conversations collected from ShareGPT.com.
Evaluation Dataset
A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT - 4 to judge the model outputs. See https://vicuna.lmsys.org/ for more details.
Major Updates of Weights v1.1
- Refactor the tokenization and separator. In Vicuna v1.1, the separator has been changed from
"###"
to the EOS token "</s>"
. This change makes it easier to determine the generation stop criteria and enables better compatibility with other libraries.
- Fix the supervised fine - tuning loss computation for better model quality.
đ§ Technical Details
The model is an auto - regressive language model based on the transformer architecture. It's fine - tuned on LLaMA using user - shared conversations from ShareGPT. The tokenization and separator are refactored in v1.1, and the supervised fine - tuning loss computation is fixed to improve model quality.
đ License
Apache License 2.0