neroai14/Nero-Qwen2.5-1.5B-Surgical
LoRA-style vs Qwen/Qwen2.5-1.5B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, up_proj changed, in 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 84/84, Attention 0/196
2 derivatives checked
- mradermacher/Nero-Qwen2.5-1.5B-Surgical-i1-GGUF: Quantization
- mradermacher/Nero-Qwen2.5-1.5B-Surgical-GGUF: Same weights, converted