FrontiersMind/Lumma-fev-0.6b
LoRA-style vs FrontiersMind/Lumma-0.6B-Base. 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 changed, in 30 of 30 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, Norms 0/91, MLP 90/90, Attention 90/90