Popular repositories Loading

1. dalla-model-training dalla-model-training Public

   Dalla training recipe using Huggingface SFT trainer

   Python 7

2. r-bpe r-bpe Public

   R-BPE: Improving BPE-Tokenizers with Token Reuse

   Python 4 2

3. dalla-data-processing dalla-data-processing Public

   data processing pipeline used for the DALLA Models.

   C

4. dalla-sentencepiece dalla-sentencepiece Public

   A tool to update an existing tokenizer model with new and common tokens from a newly trained tokenizer model. It works with any SentencePiece model.

   Python

5. .github .github Public

6. ar-ms-baseline ar-ms-baseline Public

   Training code to establish baseline for NAKBA NLP 2026: Arabic Manuscript Understanding Shared Task

   Python