ATH-MaaS/OvisOCR2
Full fine-tune vs Qwen/Qwen3.5-0.8B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Attention 213/216, Norms 127/129, Embeddings 4/4, MLP 124/124
8 derivatives checked
- Abiray/OvisOCR2-GGUF: Same weights, converted
- bartowski/ATH-MaaS_OvisOCR2-GGUF: Same weights, converted
- MDfox/OvisOCR2-GGUF-SOTA-20260823: Same weights, converted
- prithivMLmods/OvisOCR2-F32-GGUF: Same weights, converted
- mlx-community/OvisOCR2-8bit: Quantization
- manojbillionaire123/ATH-MaaS_OvisOCR2-GGUF: Same weights, converted
- Disya/OvisOCR2-GGUF: Same weights, converted
- mlx-community/OvisOCR2-6bit: Quantization
5 other repos hold byte-for-byte identical weight files.