# Unsloth Optimization

A text generation and inference model optimized using Unsloth and TRL libraries based on the Qwen/Qwen2.5-Coder-7B model, achieving 2x faster training speed

A multilingual philosophical dialogue model fine-tuned based on Qwen/Qwen3-4B, specializing in philosophy and profound topics

A reasoning-enhanced model optimized from Google Gemma-3-1B, improving logical reasoning capabilities through GRPO algorithm and high-quality datasets

Text2SQL-1.5B is a natural language to SQL model optimized based on the Qwen2 architecture, specifically designed to convert user queries into structured SQL statements.

A vision-language model trained based on Bllossom/llama-3.2-Korean-Bllossom-AICA-5B, supporting Korean and English, specializing in image-to-text and text classification tasks in the fashion domain.