mradermacher/Qari-OCR-0.3-SNAPSHOT-VL-2B-Instruct-merged-GGUF
Same weights, converted (fewer layers) vs NAMAA-Space/Qari-OCR-v0.3-VL-2B-Instruct. mradermacher/Qari-OCR-0.3-SNAPSHOT-VL-2B-Instruct-merged-GGUF matches part of NAMAA-Space/Qari-OCR-v0.3-VL-2B-Instruct (338 of its 729 tensors; the rest of NAMAA-Space/Qari-OCR-v0.3-VL-2B-Instruct has no counterpart). On the shared part: Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196