kagakouko/Spatial-Interactor-Qwen2.5-VL-3B
Partial fine-tune vs Qwen/Qwen2.5-VL-3B-Instruct. Partial change: 83% of the weights changed (attention, embeddings, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 1/2, Norms 73/138, MLP 112/304, Attention 252/380
1 derivatives checked
- mradermacher/Spatial-Interactor-Qwen2.5-VL-3B-GGUF: Same weights, converted (fewer layers)