UncannyEcho/Aura-Medium-v1-BF16
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, 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 26/144, Attention 177/184
2 derivatives checked
- mradermacher/Aura-Medium-v1-BF16-i1-GGUF: Quantization
- mradermacher/Aura-Medium-v1-BF16-GGUF: Quantization