nopenet/nope-edge
LoRA-style vs Qwen/Qwen3-4B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 108/108, Attention 144/144
4 derivatives checked
- Flexan/nopenet-nope-edge-GGUF-i1: LoRA-style
- Flexan/nopenet-nope-edge-GGUF-i3: Same weights, converted
- Flexan/nopenet-nope-edge-GGUF-i2: Not comparable yet
- mradermacher/nope-edge-GGUF: LoRA-style