arildgrimstveit/vicuna7b

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kArchitecture:Transformer Cold

The arildgrimstveit/vicuna7b is a 7 billion parameter open-source chatbot developed by the Vicuna team (UC Berkeley, CMU, Stanford, UC San Diego). It is an auto-regressive language model based on the transformer architecture, fine-tuned on 70K user-shared conversations from ShareGPT. This model is primarily intended for research and hobbyist use in large language models and chatbots, offering a strong foundation for conversational AI applications.

Loading preview...

Vicuna-7B Overview

Vicuna-7B is an open-source chatbot developed by a collaborative team from UC Berkeley, CMU, Stanford, and UC San Diego. This model is a 7 billion parameter auto-regressive language model built upon the transformer architecture, specifically fine-tuned from the LLaMA base model.

Key Characteristics & Training

  • Architecture: Transformer-based, fine-tuned from LLaMA weights.
  • Training Data: Fine-tuned on 70,000 user-shared conversations collected from ShareGPT.com, enhancing its conversational abilities.
  • Development Period: Trained between March and April 2023.
  • Evaluation: Preliminary evaluation involved GPT-4 judging model outputs on a set of 80 diverse questions, with details available in the official blog post.

Intended Use Cases

Vicuna-7B is primarily designed for:

  • Research: Ideal for academic and independent research into large language models and chatbot development.
  • Hobbyist Projects: Suitable for enthusiasts in natural language processing, machine learning, and artificial intelligence looking to experiment with conversational AI.

Note: This specific model version is a "delta model" and requires application on top of original LLaMA weights to be fully functional. Users should refer to the official instructions for proper setup. A newer version is also available.