Yashp2003/chandra-ocr-2-ggufs
Quantization vs datalab-to/chandra-ocr-2. Yashp2003/chandra-ocr-2-ggufs is a GGUF quantization (Q2_K_XL) of the same weights: 81 tensors match exactly and 130 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32