Pinned Loading

1. eellak/glossAPI eellak/glossAPI Public

   Greek Dataset Production from PDF+

   Python 134 37

2. train-apertus-with-glossapi train-apertus-with-glossapi Public

   Continued pretraining of Apertus-8B for Greek with the GlossAPI corpus — the work phase by phase: cleaning, tokenizer extension, embedding init, CPT, and parameter sweeps.

   Python