mustafaah/ScreenHighlighterRL-2B
LoRA-style vs Qwen/Qwen3-VL-2B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/217, MLP 0/196, Attention 112/208
2 derivatives checked
- mradermacher/ScreenHighlighterRL-2B-i1-GGUF: Quantization (fewer layers)
- mradermacher/ScreenHighlighterRL-2B-GGUF: Same weights, converted (fewer layers)
1 other repos hold byte-for-byte identical weight files.