nanonets/Nanonets-OCR2-1.5B-exp
Full fine-tune vs Qwen/Qwen2-VL-2B-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 2/2, Norms 163/163, MLP 180/180, Attention 240/240
2 derivatives checked
- mradermacher/Nanonets-OCR2-1.5B-exp-i1-GGUF: Quantization (fewer layers)
- mradermacher/Nanonets-OCR2-1.5B-exp-GGUF: Same weights, converted (fewer layers)
1 other repos hold byte-for-byte identical weight files.