NandiBERT-450M / modeling_nandi_encoder.py

Commit History

Yesterday

  1. Parameter counts (445M encoder, 146M for the 150M); remove internal references from code and config

    Verified signature
    5eca2f3
  2. Classifiers use the pretrained MLM head; tokenizer word spaces; README tokenizer needs trust_remote_code⁠

    Verified signature
    4acb258

2 days ago

  1. Add final checkpoint (model, config, tokenizer, remote code)

    Verified signature
    66f3476