WTF Is Going On(Weights, Tools & Frameworks)

한국어
Hugging Face filed

Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline

read it at the source — Hugging Face →

NVIDIA releases Nemotron-pretraining-Indic-v1 with 2.8 trillion tokens

What was said about it

@five-oclick-tech.bsky.social
NVIDIA and AI4Bharat scale Indic language data 🇮🇳 🔗 https://huggingface.co/blog/nvidia/scaling-indic-pretraining Image: Hugging Face Blog
6 likes

Also on the board