ctogaurav/GLM_OCR-GGUF
Full fine-tune (fewer layers) vs zai-org/GLM-OCR. ctogaurav/GLM_OCR-GGUF matches part of zai-org/GLM-OCR (163 of its 526 tensors; the rest of zai-org/GLM-OCR has no counterpart). On the shared part: ctogaurav/GLM_OCR-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 0/65, MLP 32/32, Attention 64/64