We are excited to release Llama-Nemotron-Ultra! This is a reasoning ON/OFF, dense 253B model. Open weights and post-training data. We started with llama-405B, changed it via NAS pruning then followed by reasoning-focused post-training: SFT + RL in FP8.

RT @igtmn: We've released a series of OpenReasoning-Nemotron models (1.5B, 7B, 14B and 32B) that set new SOTA on a wide range of reasoning….

RT @NVIDIAAIDev: 📣 Announcing the release of OpenReasoning-Nemotron: a suite of reasoning-capable LLMs which have been distilled from the D….

✈️ to ICML workshops to talk about the first open-weight model that outsmarted original DS-R1 on AA index. Happy to chat all things post-training and AI in general. (The poster is EXAIT workshop this Saturday)

If you are a researcher working on LLM post-training, RL and reasoning, you should really give NeMo-RL a try. Works with hugginface and megatron-core (when you need scale). Here is great blogpost by @AlexanderBukha1 and team on how to get started:

RT @BanghuaZ: Really excited to work with @AndrewYNg and @DeepLearningAI on this new course on post-training of LLMs—one of the most creat….

RT @United24media: Stop Russian nightly terror. Help Ukraine protect its skies. DONATE 👇 .

RT @RayDalio: Now that the budget bill has passed Congress, we can see what the projections look like for deficits, government debt, and de….

Post-training of LLMs is increasingly important and RLHF remains a necessary step for an overall great model. Today we are releasing 6 new reward models, including GenRMs and multilingual. These models are used to post-train next *-nemotron models.

RT @ctnzr: NVIDIA benefits greatly from the open-source community, and we're excited to be able to contribute back. It's great to see so mu….

RT @BohuslavskaKate: Kyiv this morning ‼️

RT @razomforukraine: ‼️ As G7 leaders meet in Canada, Russia sends a clear message by bombing Kyiv. Homes destroyed, kindergarten hit, civi….

RT @CAgovernor: Californians: If you’re protesting today, protect one another and hold the line for peace. There’s no place for violence i….

AI model post training is rapidly improving. The plot below (starting from the same base model) illustrates about 10 months of progress in the *open* post-training research. I’m not convinced that closed research can move as fast.

New reasoning Nemotron-H models are now publicly available. These models are based on hybrid architecture! .47B and 8B in BF16 and FP8. Blogpost: Weights:

RT @AndrewYNg: I am alarmed by the proposed cuts to U.S. funding for basic research, and the impact this would have for U.S. competitivenes….

NVIDIA Blackwell: The Journey From Die to Data Center via @YouTube.

RT @nvidianewsroom: NVIDIA today reported record revenue for Q1 FY26 of $44.1 billion, up 12% from the previous quarter and up 69% from a y….

RT @ctnzr: Nemotron-CORTEXA just reached the top of the SWEBench leaderboard for using LLMs to solve software engineering problems, solving….

RT @rshereme: Russia killed them. This morning, while you were having breakfast and coffee, russians murdered three Ukrainian children.….

RT @maria_avdv: Brutal night for Kyiv and all of Ukraine. Russia launched massive combined attack on civilians: ballistic missiles, Shahed….