wayu-ai/wayu-paxa-ocr-zero-gguf
Same weights, converted (fewer layers) vs wayu-ai/wayu-paxa-ocr-zero. wayu-ai/wayu-paxa-ocr-zero-gguf matches part of wayu-ai/wayu-paxa-ocr-zero (165 of its 608 tensors; the rest of wayu-ai/wayu-paxa-ocr-zero has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/37, MLP 0/54, Attention 0/72