ReadyArt/Melody1437-12B
LoRA-style vs google/gemma-4-12B-it. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/12, Norms 0/289, other 0/48, MLP 96/144, Attention 184/184
4 derivatives checked
- ReadyArt/Melody1437-12B-GGUF: Quantization
- mradermacher/Melody1437-12B-GGUF: Quantization
- sebidev/Melody1437-12B-GGUF: Quantization
- mradermacher/Melody1437-12B-i1-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.