{"type":"post","id":"nvidia-and-ai4bharat-publish-nemotron-pretraining-indic-v1-77b559","slug":"nvidia-and-ai4bharat-publish-nemotron-pretraining-indic-v1-77b559","title":"NVIDIA and AI4Bharat publish Nemotron-Pretraining-Indic-v1 and Indic-LLM-Eval-Suite","description":"NVIDIA and AI4Bharat describe an open corpus of roughly 2.83 trillion tokens across 22 scheduled Indian languages, alongside a reusable synthetic-data pipeline and an Indic-language evaluation suite.","retrieval_nugget":"NVIDIA and AI4Bharat describe an open corpus of roughly 2.83 trillion tokens across 22 scheduled Indian languages, alongside a reusable synthetic-data pipeline and an Indic-language evaluation suite. Their continued-pretraining experiments report gains in knowledge and reasoning when synthetic material is mixed with natural Indic text, offering researchers shared resources to test and extend.","published_at":"2026-11-09","updated_at":"2026-11-09","record_date":"2026-11-09","date_kind":"published_at","topics":["models","evals","open-source"],"entities":["NVIDIA","AI4Bharat","Nemotron-Pretraining-Indic-v1","Indic-LLM-Eval-Suite","NeMo-Gym","Gemma-4"],"related_patterns":["ai-engineering-evaluations-are-splitting-into-task-specific"],"novelty_label":"new_fact","source_url":"https://arxiv.org/html/2610.26006","source_urls":["https://arxiv.org/html/2610.26006"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:nvidia-and-ai4bharat-publish-nemotron-pretraining-indic-v1-77b559","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/nvidia-and-ai4bharat-publish-nemotron-pretraining-indic-v1-77b559/","markdown":"https://newruntime.com/posts/nvidia-and-ai4bharat-publish-nemotron-pretraining-indic-v1-77b559.md","json":"https://newruntime.com/posts/nvidia-and-ai4bharat-publish-nemotron-pretraining-indic-v1-77b559.json"},"markdown_url":"https://newruntime.com/posts/nvidia-and-ai4bharat-publish-nemotron-pretraining-indic-v1-77b559.md","next_reads":[{"type":"topic","path":"/topics/models/","url":"https://newruntime.com/topics/models/","title":"Models","reason":"Explore the models topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/models.md","json_url":"https://newruntime.com/topics/models.json"},{"type":"topic","path":"/topics/evals/","url":"https://newruntime.com/topics/evals/","title":"Evals","reason":"Explore the evals topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/evals.md","json_url":"https://newruntime.com/topics/evals.json"},{"type":"topic","path":"/topics/open-source/","url":"https://newruntime.com/topics/open-source/","title":"Open Source","reason":"Explore the open-source topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/open-source.md","json_url":"https://newruntime.com/topics/open-source.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}