Nathan Lambert

natolambert.bsky.social

06 April 2025 09:07

RL backlog -- some extra RL / reasoning notes I’ve been sitting on (or forgot about): 1. OpenAI’s many forms of RL, 2. On distilling chain of thoughts vs. RL, 3. Did DeepSeek distill o1?, and 4. Why latent reasoning is so interesting.

Alexander Doria

dorialexander.bsky.social

12 February 2025 13:24

I have to admit that except for the occasional cross-posting, not sure I’ll keep very active on here. There was a big opportunity to migrate the core AI/ML community that was unfortunately squandered with all this hf dataset backlash.

Nathan Lambert

natolambert.bsky.social

11 February 2025 16:18

Best part of this that Luca isn’t highlighting to start is that we trained a way better OLMoE for this too. All from better annealing and post train. Didn’t need to redo pre training. Goes to show how much potential these models have! new instruct model: huggingface.co/allenai/OLMo...

François Fleuret

francois.fleuret.org

06 December 2024 10:45

My brain after years of research in ML/DL is a wasteland of broken intuition pumps. Seriously NOTHING BEHAVES LIKE IT SHOULD.

Kapalı içerik