🔥Telegram İfşa

Announcing the ICLR 2026 Call for Papers! Abstract submission: Sept 19 (AoE) Paper submission: Sept 24 (AoE) Reviews released: Nov 11 Author/Reviewer discussion: Nov 11-Dec 3 Final decisions: Jan 22 2026 iclr.cc/Conferences/20…

🚀 Introducing Qwen3-4B-Instruct-2507 & Qwen3-4B-Thinking-2507 — smarter, sharper, and 256K-ready! 🔹 Instruct: Boosted general skills, multilingual coverage, and long-context instruction following. 🔹 Thinking: Advanced reasoning in logic, math, science & code — built for

Today we're releasing NVIDIA Nemotron Nano v2 - a 9B hybrid SSM that is 6X faster than similarly sized models, while also being more accurate. Along with this model, we are also releasing most of the data we used to create it, including the pretraining corpus. Links to the

We are excited to release Nvidia-Nemotron-Nano-V2 model! This is a 9B hybrid SSM model with open base model and training data. This model also supports runtime "thinking" budget control. HF collection with base and post trained models: huggingface.co/collections/nv…

Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset. arxiv.org/abs/2508.15096

NVIDIA open-sourced a large, high-quality math corpus, nvidia/Nemotron-CC-Math The corresponding paper explains how it turns messy web pages into a clean, massive math dataset that boosts reasoning. 5.5x larger than the previous best high quality math set. Most math online

As part of Nemotron, we're releasing a new Math dataset, made by rendering webpages using Lynx and then using an LLM to rewrite the result into LaTeX. Our models got much better at math when we started using this dataset. We hope it's helpful to the community. 💚

Nemotron-CC-Math is a 133B-token *benchmark-agnostic, pretraining dataset* built entirely from CommonCrawl. huggingface.co/datasets/nvidi…

Enjoy the math pretraining dataset from our team used to train our recently released Nvidia-Nemotron-Nano-V2 model!

Also big congrats on Nemotron-CC-Math! 🎉 NVIDIA is not only leading, but continuing to lead, and setting the pace across multiple subareas of open pretraining data. Rabeeh Karimi and Sanjeev Satheesh are the leading authors there! arxiv.org/pdf/2508.15096

Do you want to work on LLM and DLM model post-training with us? Jiantao Jiao is hiring! nvidia.wd5.myworkdayjobs.com/NVIDIAExternal…

💬 “We're trying to make the most open approach to AI development that the world has ever seen.” 💡 Openness isn’t optional — it’s essential for the future of AI. That’s why Nemotron was built: to set new standards for speed, transparency, and versatility in enterprise AI.

A great video by Bryan Catanzaro on what Nemotron is and why it is open youtu.be/_y9SEtn1lU8?si… !