NVIDIAAnalysisAI ModelsOctober 16, 2026

Nvidia scales Indic pretraining to 2.8T tokens with open data pipeline

Read original source →huggingface.co

Hugging Face post details an Indic-language pretraining run at 2.8 trillion tokens, paired with an open data generation pipeline. The pipeline is released openly rather than kept proprietary.

1 source

More stories today

Open the live feed