ertghiu256/Qwen3-4b-2507-Thinking-math-and-code

Qwen 3 4b 2507 Thinking Math & Code

Uploaded finetuned model

• Developed by: ertghiu256
• License: apache-2.0
• Finetuned from model : unsloth/qwen3-4b-thinking-2507-unsloth-bnb-4bit
• Other config : dataset = "ertghiu256/MathReasoning-with-code-samples", max_steps = 150, learning_rate = 6e-5

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.