AdaptLLM/remote-sensing-Qwen2-VL-2B-Instruct
Partial fine-tune vs Qwen/Qwen2-VL-2B-Instruct. Partial change: 70% of the weights changed (attention, embeddings, mlp, norms), in 28 of 32 layers.
Tensors changed: Embeddings 1/2, Norms 46/187, MLP 84/216, Attention 196/324
1 derivatives checked
- mradermacher/remote-sensing-Qwen2-VL-2B-Instruct-GGUF: Same weights, converted (fewer layers)