Tagged: grpo

6 articles

Latest

Liquid AI's 350M model hits 22.6% schema compliance before fine-tuning

Tulu 3's full post-training stack squeezed into a single 16GB Colab GPU

Intel's DeepMath slashes AI reasoning bloat by 66% using tiny Python snippets

A tiny 0.6B model just crushed formal math proofs, topping the MiniF2F leaderboard

DeepSpeed ZeRO-3 clashing with Liger GRPO loss? Shape mismatch halts Qwen2.5 finetuning

How a 3B open model taught itself to rethink math—no human data needed