NandiBERT: open-source SoTA Indian language encoders in 150M and 450M sizes
kalyan_kpl · x · 2026-11-21
FrontiersMind released NandiBERT, described as an open-source SoTA encoder model family for Indian languages, available on Hugging Face under Apache-2.0 in 150M and 450M variants.
- Claims to outperform IndicBERTv2, ModernBERT, and Ettin encoder models
- Covers 20+ languages including Hindi, Tamil, Telugu, Bengali, Urdu, plus English
- Fill-mask masked language model, loadable via transformers
Related event: FrontiersMind Open-Sources NandiBERT, an India-Focused Language Encoder(5 posts)→
More from Models
- Leaked Gemini App screenshot exposes internal reasoning and system prompt with teen safety rules — Bigwaliwigi · 2026-11-21
- NandiBERT-150M and 450M weights now live on Hugging Face under Apache 2.0 — kalyan_kpl · 2026-11-21
- OpenAI researcher hints at mystery model "Inkling" in babysitting tweet — yiwenyuan98 · 2026-11-21
- LlamaIndex benchmark: Gemini 4 Neon leads tables and visual grounding at 6.2¢/page — llama_index · 2026-11-21
- Inkling 2 Mini quantized to 13.9GB runs at ~60 t/s decode on a single RTX 4090 — indrasmirror · 2026-11-21
- Claude Code reportedly beat GTA VI solo in 12 hours, digging up 500+ hidden secrets — nikola_mr64990 · 2026-11-21