Vikhrmodels/Vikhr-2-VL-2b-Instruct-experimental
LoRA-style vs Qwen/Qwen2-VL-2B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 28 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, Norms 0/187, MLP 0/216, Attention 56/324
1 derivatives checked
- mradermacher/Vikhr-2-VL-2b-Instruct-experimental-GGUF: Same weights, converted (fewer layers)