mradermacher/olmOCR-7B-grpo-v3-i1-GGUF
Full fine-tune (fewer layers) vs suv11235/olmOCR-7B-grpo-v3. mradermacher/olmOCR-7B-grpo-v3-i1-GGUF matches part of suv11235/olmOCR-7B-grpo-v3 (339 of its 729 tensors; the rest of suv11235/olmOCR-7B-grpo-v3 has no counterpart). On the shared part: mradermacher/olmOCR-7B-grpo-v3-i1-GGUF is a GGUF (Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 37/57, MLP 84/84, Attention 166/196, lm_head 1/1