RituGujela100/gemma-qlora-customer-support
LoRA-style vs google/gemma-1.1-2b-it. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 18 of 18 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/37, MLP 0/54, Attention 36/72