Qwen3-4B-Thinking-2507-GPT-5.2-High-Reasoning-Distill/README.md

base_model, tags, license, datasets

base_model	tags	license	datasets
unsloth/Qwen3-4B-Thinking-2507	text-generation-inference transformers unsloth qwen3	apache-2.0	TeichAI/gpt-5.2-high-reasoning-250x

Qwen3 4B Thinking 2507 x GPT 5.2 (High Reasoning)

This model was trained on 250 examples generated by GPT 5.2 (high reasoning)

Note: In this distill I fixed formatting issues found in previous gpt 5 distills. Will be going back to update the other 5.2 distills

• Developed by: TeichAI
• Finetuned from model : unsloth/qwen3-4b-thinking-2507

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