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

2026-10-17来源 Hacker News NewEnglish

原文:https://www.a8q9.cn/en/article/scaling-indic-pretraining-2-8t-tokens-and-an-open-data-generation-pipeline-3bf95b.html

相关文章