remyxai/SpaceQwen2.5-VL-3B-Instruct
LoRA-style vs Qwen/Qwen2.5-VL-3B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, Norms 0/138, MLP 0/304, Attention 72/380
2 derivatives checked
- mradermacher/SpaceQwen2.5-VL-3B-Instruct-i1-GGUF: Quantization (fewer layers)
- mradermacher/SpaceQwen2.5-VL-3B-Instruct-GGUF: Same weights, converted (fewer layers)