DevQuasar/nanonets.Nanonets-OCR-s-GGUF
Quantization (fewer layers) vs nanonets/Nanonets-OCR-s. DevQuasar/nanonets.Nanonets-OCR-s-GGUF matches part of nanonets/Nanonets-OCR-s (434 of its 824 tensors; the rest of nanonets/Nanonets-OCR-s has no counterpart). On the shared part: DevQuasar/nanonets.Nanonets-OCR-s-GGUF is a GGUF quantization (Q8_0) of the same weights: 181 tensors match exactly and 253 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252