prithivMLmods/Camel-Doc-OCR-080125
Full fine-tune vs Qwen/Qwen2.5-VL-7B-Instruct. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/2, Norms 57/122, MLP 276/280, Attention 324/324, lm_head 1/1
3 derivatives checked
- prithivMLmods/Camel-Doc-OCR-080125-GGUF: Same weights, converted (fewer layers)
- mradermacher/Camel-Doc-OCR-080125-i1-GGUF: Quantization (fewer layers)
- mradermacher/Camel-Doc-OCR-080125-GGUF: Same weights, converted (fewer layers)