prithivMLmods/Perseus-Doc-VL-0712
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 61/122, MLP 280/280, Attention 324/324, lm_head 1/1
4 derivatives checked
- mradermacher/Perseus-Doc-vl-0712-i1-GGUF: Quantization (fewer layers)
- mradermacher/Perseus-Doc-vl-0712-GGUF: Same weights, converted (fewer layers)
- mradermacher/Perseus-Doc-vl-071225-i1-GGUF: Quantization (fewer layers)
- mradermacher/Perseus-Doc-vl-071225-GGUF: Same weights, converted (fewer layers)