Rufus-Air: An Open LLM Post-Training Recipe
Ranking
Overall
89
Content
100
Popularity
64
Observed public metrics from 1 member.
Merged summary
TL;DR - Rufus-Air presents an open, reproducible eight-stage post-training recipe for the 106B-parameter GLM-4.5-Air-Base model. It demonstrates that carefully ordered training stages, reliable rewards, prompt filtering, and infrastructure choices can produce results competitive with similarly sized open models.
- The pipeline combines SFT, specialized reasoning/coding/instruction-following RL, agent training, and final RLHF.
- Stages move from foundational to advanced capabilities and from verifiable rewards toward softer judge-based signals.
- Diverse high-quality SFT establishes the capability baseline, while difficulty filtering keeps RL prompts within a productive range.
- The recipe uses open-source components and public data without new human annotation or an internal distillation teacher.
Sources (1)
Rufus-Air: An Open LLM Post-Training Recipe
Public signals
Hugging Face upvotes 11
TL;DR - Rufus-Air presents an open, reproducible eight-stage post-training recipe for the 106B-parameter GLM-4.5-Air-Base model. It demonstrates that carefully ordered training stages, reliable rewards, prompt filtering, and infrastructure choices can produce results competitive with similarly sized open models.
- The pipeline combines SFT, specialized reasoning/coding/instruction-following RL, agent training, and final RLHF.
- Stages move from foundational to advanced capabilities and from verifiable rewards toward softer judge-based signals.
- Diverse high-quality SFT establishes the capability baseline, while difficulty filtering keeps RL prompts within a productive range.
- The recipe uses open-source components and public data without new human annotation or an internal distillation teacher.