Overview

Vigogne-7B-Chat is a 7 billion parameter LLaMA-based model developed by bofenghuang, specifically fine-tuned for multi-turn dialogues in French. It aims to provide a conversational AI assistant experience for French users. The model is intended for research use only, adhering to the same usage and license notices as Stanford Alpaca, with its dataset licensed under CC BY NC 4.0 for non-commercial use.

Key Capabilities

• French Multi-turn Dialogue: Optimized for engaging in extended conversations in French between a human user and an AI assistant.
• LLaMA-based Architecture: Built upon the LLaMA-7B foundation model.
• Research-Oriented: Primarily designed for academic and research applications in natural language processing.

Limitations

• The model is still under development and may generate harmful, biased, incorrect, or unhelpful content.
• Strictly licensed for non-commercial research use only.

Good For

• Developing and experimenting with French-speaking conversational AI agents.
• Research into fine-tuning large language models for specific languages and dialogue tasks.
• Academic projects requiring a French-language chat model.