Vicuna-13B

Vicuna-13B v1.5 is an advanced chat assistant that engages in natural language conversations. It was developed by LMSYS and fine-tuned from the Llama 2 model using user-shared conversations collected from ShareGPT.

Key features:
- Auto-regressive language model based on the transformer architecture
- Designed primarily for research purposes in natural language processing, machine learning, and artificial intelligence
- Licensed under the Llama 2 Community License Agreement

How it works:
Vicuna v1.5 uses supervised instruction fine-tuning on approximately 125,000 conversations collected from ShareGPT.com. Detailed training procedures and data handling methods are available in the appendix of the associated research paper.

Use of AI:
The primary use of Vicuna is for research on large language models and chatbots. It is intended for researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.

AI foundation model:
Vicuna-13B v1.5 is fine-tuned from the Llama 2 model.

How to access:
- Command line interface: FastChat CLI
- APIs: OpenAI API, Huggingface API

Vicuna is evaluated using standard benchmarks, human preference assessments, and LLM-as-a-judge methodologies. Detailed evaluation results and comparisons with other models can be found in the associated research paper and leaderboard.

The Vicuna model has undergone several iterations, with each version incorporating improvements based on user feedback and additional training data. Specific differences between versions are documented in the model's release notes and associated research papers.