nschlaepfer / ChainForge-R1-SuperCoTView on GitHub
A multi-stage pipeline that enhances Qwen2.5 language models with DeepSeek Reasoner's chain-of-thought capabilities. Implements the DeepSeek-R1 methodology through cold-start SFT, reasoning-oriented RL, rejection sampling, and optional model distillation.
☆11Sep 15, 2025Updated last year

Alternatives and similar repositories for ChainForge-R1-SuperCoT

Users that are interested in ChainForge-R1-SuperCoT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?