gywy/mamba-765M-chinese-chat-v0.1
The gywy/mamba-765M-chinese-chat-v0.1 is a 0.79 billion parameter Mamba-based model developed by gywy, fine-tuned for Chinese chat applications. It has undergone Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to enhance its instruction-following capabilities. With a context length of 32768 tokens, this model is designed for generating coherent and relevant responses in Chinese conversational tasks.
Loading preview...
Overview
gywy/mamba-765M-chinese-chat-v0.1 is a 0.79 billion parameter language model built on the Mamba architecture, specifically designed for Chinese chat interactions. Developed by gywy, this model has been further refined through Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to significantly improve its ability to follow instructions and generate appropriate responses in conversational contexts. It supports a substantial context length of 32768 tokens, allowing for more extensive and nuanced dialogues.
Key Capabilities
- Enhanced Instruction Following: Improved through SFT and DPO, enabling better adherence to user prompts.
- Chinese Chat Optimization: Specifically tuned for generating natural and relevant text in Chinese conversational scenarios.
- Long Context Understanding: Capable of processing and generating text within a 32768-token context window.
Good for
- Developing Chinese-language chatbots and conversational AI agents.
- Applications requiring instruction-tuned models for generating creative or informative text in Chinese.
- Scenarios where a compact yet capable model with good instruction-following is needed for Chinese text generation.