AI News
Tulu 3's full post-training stack squeezed into a single 16GB Colab GPU
MarkTechPost · Aug 12, 2026 · 2 min read
AllenAI's Open Instruct framework powers Tulu 3, but running its full post-training pipeline typically demands a multi-...
Topic: grpo
5 articles
Explore our coverage of grpo — 5 curated articles, summaries, and related resources from the Inblix archive.
Research
Intel's DeepMath slashes AI reasoning bloat by 66% using tiny Python snippets
Hugging Face Blog · Dec 4, 2025 · 2 min read
Intel researchers have built DeepMath, a math agent that trades the long-winded, error-prone text chains of typical LLM...
Research
A tiny 0.6B model just crushed formal math proofs, topping the MiniF2F leaderboard
Hugging Face Blog · Aug 14, 2025 · 2 min read
A new open-source training recipe is producing absurdly strong theorem-proving models that fit on a laptop. The team be...
Research
DeepSpeed ZeRO-3 clashing with Liger GRPO loss? Shape mismatch halts Qwen2.5 finetuning
Hugging Face Blog · May 25, 2025 · 2 min read
Another day, another obscure shape mismatch tearing through a perfectly good training run. This time, the culprit is a...
Research
How a 3B open model taught itself to rethink math—no human data needed
Hugging Face Blog · Jan 31, 2025 · 2 min read
The release of DeepSeek-R1 sent a jolt through the AI world. Here was an open model going toe-to-toe with OpenAI's o1 o...