Vicuna-33B

Vicuna-33B v1.3 is an advanced chat assistant developed by LMSYS for research purposes in natural language processing, machine learning, and artificial intelligence. It is fine-tuned from the LLaMA model using user-shared conversations from ShareGPT.

Key features:
- Auto-regressive language model based on the transformer architecture
- Fine-tuned from LLaMA with supervised instruction fine-tuning
- Trained on approximately 125K conversations collected from ShareGPT.com
- Evaluated using standard benchmarks, human preference, and LLM-as-a-judge methodologies
- Released under a non-commercial license

How it works:
Vicuna-33B v1.3 is an auto-regressive language model that generates human-like responses to user inputs. It has been fine-tuned from the LLaMA model using a dataset of user-shared conversations from ShareGPT.com, allowing it to engage in more natural and contextually relevant conversations.

Integrations:
- Command line interface: FastChat CLI
- APIs: OpenAI API, Huggingface API

Use of AI:
Vicuna-33B v1.3 is an AI-powered chat assistant that leverages large language models and transformer architecture to generate human-like responses. It has been trained on a vast amount of conversational data, enabling it to understand and respond to a wide range of user inputs.

AI foundation model:
Vicuna-33B v1.3 is fine-tuned from the LLaMA (Large Language Model Assistant) model, which is a foundational language model developed by Facebook AI Research.

How to access:
- GitHub repository: https://github.com/lm-sys/FastChat
- Online demo: https://chat.lmsys.org/

For more detailed information, refer to the Vicuna Model Card on Hugging Face, the LMSYS blog, and the associated research paper on arXiv.