ModernBERT For Named Entity Recognition. Finetuned on Conll2003 dataset.

[jayeshthk]

Changes

ModernBERT - NER finetune version offers token classification over long range of tokens(~8k). Making it one of the best encoder-only models for long context token classification.

• Also, finetuned Model hosted on huggingface showing a great accuracy over NER datasets -> https://huggingface.co/joe-xhedi/ModernBERT-NER

Tests

• Is the new feature tested? (Not always necessary for all changes -- just adding to the checklist to keep track)
• Have you ran all the tests?
• Do the tests all pass?
• If not, have you included an explanation of which tests this PR breaks and/or why (below this checklisT)