lmsys/vicuna-13b-v1.1

TEXT GENERATIONConcurrency Cost:1Model Size:13BQuant:FP8Ctx Length:4kPublished:Apr 12, 2023Architecture:Transformer0.1K Cold

Vicuna-13B-v1.1 is a 13 billion parameter auto-regressive language model developed by LMSYS, fine-tuned from LLaMA. It is specifically designed as a chat assistant, trained on approximately 70K user-shared conversations from ShareGPT. This model excels in conversational AI research and chatbot development, offering enhanced dialogue capabilities.

Loading preview...

Vicuna-13B-v1.1: A Chat Assistant Model

Vicuna-13B-v1.1 is a 13 billion parameter auto-regressive language model developed by LMSYS, fine-tuned from the LLaMA architecture. Its primary distinction lies in its training methodology: it was fine-tuned using supervised instruction on a dataset of approximately 70,000 user-shared conversations collected from ShareGPT. This specialized training focuses on enhancing its capabilities as a chat assistant.

Key Capabilities

  • Conversational AI: Optimized for generating human-like responses in dialogue settings.
  • Research Tool: Primarily intended for research in large language models and chatbots.
  • LLaMA-based: Leverages the foundational architecture of LLaMA for its language understanding and generation.

Good For

  • Researchers: Ideal for academics and practitioners exploring advancements in natural language processing, machine learning, and artificial intelligence, particularly in the domain of conversational agents.
  • Hobbyists: Suitable for individuals interested in experimenting with and developing chatbots.
  • Chatbot Development: Provides a strong base for building and evaluating chat-oriented applications.