mradermacher/Qari-OCR-0.2.2.1-VL-2B-Instruct-merged-GGUF
Same weights, converted (fewer layers) vs oddadmix/Qari-OCR-0.2.2.1-VL-2B-Instruct-merged. mradermacher/Qari-OCR-0.2.2.1-VL-2B-Instruct-merged-GGUF matches part of oddadmix/Qari-OCR-0.2.2.1-VL-2B-Instruct-merged (338 of its 729 tensors; the rest of oddadmix/Qari-OCR-0.2.2.1-VL-2B-Instruct-merged 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