bartowski/allenai_olmOCR-7B-0225-preview-GGUF
Quantization (fewer layers) vs allenai/olmOCR-7B-0225-preview. bartowski/allenai_olmOCR-7B-0225-preview-GGUF matches part of allenai/olmOCR-7B-0225-preview (339 of its 730 tensors; the rest of allenai/olmOCR-7B-0225-preview has no counterpart). On the shared part: bartowski/allenai_olmOCR-7B-0225-preview-GGUF is a GGUF quantization (Q8_0) of the same weights: 141 tensors match exactly and 198 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1