Mungert/olmOCR-7B-0225-preview-GGUF
Full fine-tune (fewer layers) vs Qwen/Qwen2-VL-7B-Instruct. Mungert/olmOCR-7B-0225-preview-GGUF matches part of Qwen/Qwen2-VL-7B-Instruct (339 of its 730 tensors; the rest of Qwen/Qwen2-VL-7B-Instruct has no counterpart). On the shared part: Mungert/olmOCR-7B-0225-preview-GGUF is a GGUF (Q4_K) of different weights. Fine-tune: 93% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 53/57, MLP 84/84, Attention 196/196, lm_head 1/1