AI4BharatIndicBERT
IndicBERT v2 Masked Language Model
This 278M-parameter IndicBERT v2 release uses a distinct training configuration: Masked-language pretraining on IndicCorp v2.
The objective distinguishes this checkpoint
The model card links separate weights for the MLM, Samanantar, back-translation and shared-script experiments. These are training variants, not different service tiers.IndicBERT v2 Masked Language Model official model card
Control the downstream comparison
Practical guidance. Use this as the reference when comparing the additional parallel-data objectives. Keep downstream data and tuning settings fixed.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | IndicBERTv2-MLM-only |
| License | MIT.IndicBERT v2 Masked Language Model official model card |
| Evaluation | IndicXTREME; the release supports downstream classification, entity extraction, question answering and retrieval research.IndicBERT v2 Masked Language Model official model card |
Related models
- IndicBERT v2 Samanantar TLM
AI4Bharat ยท IndicBERT
IndicBERT v2 encoder combining masked-language training with Samanantar translation-language modeling.
Launch date not confirmedDownloadable