Vicuna-7B-V1.3 Open-Source Chat Assistant - Free Deployment for Unrestricted Chat on Various Topics

Home

Vicuna 7b V1.3

Developed by lmsys

Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared dialogues collected from ShareGPT.

Large Language Model

Transformers

#User Dialogue Fine-tuning #LLaMA-derived Model #Non-commercial Use

Downloads 15.52k

Release Time : 6/18/2023

Model Overview

Vicuna is a chat assistant model based on LLaMA, primarily used for natural language processing and chatbot research.

Model Features

High-quality Dialogue Capability

Fine-tuned on user-shared dialogue data from ShareGPT, enabling fluent conversational interactions

Open-source Accessibility

Code and weight files are open-sourced on GitHub, facilitating research and secondary development

Multi-evaluation Validation

Model performance validated through standard benchmarks, human preference evaluations, and LLM-as-a-judge methods

Model Capabilities

Text Generation

Dialogue Interaction

Instruction Understanding & Execution

Natural Language Processing Research

Use Cases

Academic Research

Large Language Model Research

Used to study the behavior and performance of dialogue systems

Performs well on multiple evaluation benchmarks

Application Development

Intelligent Chatbot

Develop AI assistants with natural conversational abilities

🚀 Vicuna Model Card

Vicuna is a chat assistant trained by fine - tuning LLaMA on user - shared conversations, aiming to support research on large language models and chatbots.

🚀 Quick Start

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.

✨ Features

Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. It serves as a valuable tool for research on large language models and chatbots.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

📚 Documentation

Model Details

Developed by: LMSYS
Model type: An auto-regressive language model based on the transformer architecture.
License: Non-commercial license
Finetuned from model: LLaMA.

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 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.

Training Details

Vicuna v1.3 is fine-tuned from LLaMA 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.

Difference between different versions of Vicuna

See vicuna_weights_version.md

🔧 Technical Details

No specific technical details (more than 50 words) are provided in the original document, so this section is skipped.

📄 License

The model uses a non - commercial license.

⚠️ Important Note

New version available. Please check out a newer version of the weights here.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご