DevQuasar/nanonets.Nanonets-OCR2-3B-GGUF

Same weights, converted (fewer layers) vs nanonets/Nanonets-OCR2-3B. DevQuasar/nanonets.Nanonets-OCR2-3B-GGUF matches part of nanonets/Nanonets-OCR2-3B (434 of its 824 tensors; the rest of nanonets/Nanonets-OCR2-3B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252

On the Hub · Downloads on Model Pulse