# GRPO Fine-tuning

Vietnamese Retrieval-Augmented Generation (RAG) specialized large model fine-tuned based on Qwen2.5-7B-Instruct, trained using GRPO optimization method

A fine-tuned SQL generation model based on QwenCoder, supporting multiple dialects with excellent performance

A 3-billion-parameter language model trained with reinforcement learning for solving mathematical reasoning tasks, especially countdown games.

Gemma-3-4b Reasoning is a Transformer-based language model fine-tuned using the GRPO method, specializing in reasoning task optimization.

A medical domain-specific model based on Qwen2.5-3B-Instruct, excelling in medical reasoning and mathematical problem-solving