Open Source9d ago

Detected, not submitted

Hindi ModernBERT

Own Hindi ModernBERT?

Verify your site to claim this listing and get emailed the moment a buyer's looking for something like it.

This is mine — claim it
Hindi ModernBERT preview

A 188M parameter Hindi language encoder with 8K context length trained on 28.5B tokens, achieving state-of-the-art results on Hindi retrieval benchmarks.

Spotted on Hacker News on September 7, 2026.

KK

kkkamur

Maker