Home
AI Tools
AI Models
MCP
AI NEWS
EN
Model Selection
Tags
Japanese Instruction Fine-tuning
# Japanese Instruction Fine-tuning
Openrs3 GRPO Ja
OpenRS3-GRPO-ja is a fine-tuned version of the SakanaAI/TinySwallow-1.5B-Instruct model on a Japanese mathematical instruction dataset, trained using the GRPO method, focusing on mathematical reasoning tasks.
Large Language Model
Transformers
O
EQUES
25
3
Featured Recommended AI Models
Empowering the Future, Your AI Solution Knowledge Base
English
简体中文
繁體中文
にほんご
© 2025
AIbase