AI4BharatRomanSetu
RomanSetu Base SFT Native
RomanSetu Base SFT Native is a distinct instruction-tuned checkpoint in the RomanSetu study.
Research release
The training order defines this research checkpoint
Instruction tuning is applied directly to the base model using native-script data.RomanSetu training configurations and published checkpoints
Keep native and Romanized evaluations separate
Practical guidance. A model's answer quality and its token efficiency are different measurements. Compare the script representation the model was trained to use, then inspect semantic accuracy.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | romansetu-base-sft-native |
| Terms | Llama 2 license.RomanSetu Base SFT Native official model card |
| Languages | English, Hindi, Marathi, Gujarati, Tamil and Malayalam.RomanSetu Base SFT Native official model card |
Related models
- RomanSetu Base SFT Romanized
AI4Bharat ยท RomanSetu
Llama 2 research adaptation with instruction training directly on Romanized data.
Launch date not confirmedResearch releaseDownloadable