ganchengguang/Yoko-7B-Japanese-v0
ganchengguang/Yoko-7B-Japanese-v0 is a 7 billion parameter LLaMA2-based causal language model fine-tuned by ganchengguang using QLoRA. It was trained on a subset of the Guanaco dataset, specifically 49,000 chat samples, and demonstrates improved performance in Chinese and Japanese language tasks. This model is suitable for chat-based applications requiring enhanced multilingual capabilities, particularly in East Asian languages.
Loading preview...
Model Overview
Yoko-7B-Japanese-v0 is a 7 billion parameter language model developed by ganchengguang, fine-tuned from the vanilla LLaMA2-7B architecture using QLoRA. This model was specifically trained on 49,000 chat samples from the Guanaco dataset, with contributions from Yokohama National University Mori Lab.
Key Capabilities
- Enhanced Multilingual Performance: Demonstrates improved performance in both Chinese and Japanese language processing, making it suitable for applications targeting these languages.
- Efficient Fine-tuning: Utilizes QLoRA for fine-tuning, allowing for efficient adaptation of the base LLaMA2 model.
- Chat-oriented Training: Trained on chat samples, indicating a focus on conversational AI tasks.
Recommended Usage
This model is particularly well-suited for:
- Chatbots and Conversational AI: Its training on chat samples makes it effective for dialogue systems.
- Applications requiring Chinese and Japanese language support: The model's improved performance in these languages is a key differentiator.
Generation Parameters
For optimal results, the following generation parameters are recommended:
temperature: 0.5 to 0.7top_p: 0.65 to 1.0top_k: 30 to 50repeat_penalty: 1.03 to 1.17