prithivMLmods/Gliese-OCR-7B-Post2.0-final-GGUF

Same weights, converted (fewer layers) vs prithivMLmods/Gliese-OCR-7B-Post2.0-final. prithivMLmods/Gliese-OCR-7B-Post2.0-final-GGUF matches part of prithivMLmods/Gliese-OCR-7B-Post2.0-final (339 of its 729 tensors; the rest of prithivMLmods/Gliese-OCR-7B-Post2.0-final has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1

On the Hub · Downloads on Model Pulse