Clef: Open-source decision models, and new RL fine-tuning platform

Re:Clef: Open-source decision models, and new RL fine-tuning... by teleforce on Thursday October 01, 2026 @11:09PM (#49929481)

In "How we trained Clef" section Cloudflare mentioned that they initially based their Jev-like system on DiffussionGemma (DJev) model but then changed to Qwen with post training for Clef, but never mentioned any reason and justification for the change.

Although they included the benchmark against DJev and Clef is better, perhaps if you can test it to see the real-world performance.

[ Parent | on HN ]

Re:Clef: Open-source decision models, and new RL fine-tuning... by nostrebored on Thursday October 01, 2026 @11:45PM (#49929632)

Diffusion Gemma sucks to train if you are not already mostly in distribution. The reason diffusion Gemma is fast is a learned denoising that balances quality and speed. So the further your data is from what already happens, the slower it gets. In almost every case I’ve tried, you might as well just train Nemotron.

[ Parent | on HN ]