Tokenization on AI4Bharat Sangraha Punjabi
210Token CountBrahmicTokenizer-131K
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BrahmicTokenizer-131KEvaluation Protocol=27M-document Indic pretraining corpus2026.05 | 210 | — | |
| Sarvam-1Evaluation Protocol=27M-document Indic pretraining corpus2026.05 | 139 | -34 | |
| Sarvam-30BEvaluation Protocol=27M-document Indic pretraining corpus2026.05 | 138 | -34.5 | |
| Tekken/SmEvaluation Protocol=27M-document Indic pretraining corpus2026.05 | — | 22.4 |