prithivMLmods/Garnet-OCR-3B-0422
Full fine-tune vs prithivMLmods/Megalodon-OCR-Sync-0713. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Norms 80/138, MLP 284/304, Attention 380/380, Embeddings 1/1
3 derivatives checked
- mradermacher/Garnet-OCR-3B-0422-i1-GGUF: Quantization (fewer layers)
- mradermacher/Garnet-OCR-3B-0422-GGUF: Same weights, converted (fewer layers)
- prithivMLmods/Garnet-OCR-3B-0422-GGUF: Same weights, converted (fewer layers)