r1char9/t5gemma2-detox-ru-en
LoRA-style vs google/t5gemma-2-1b-1b. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 26 of 27 layers; norms, biases and embeddings are untouched.
Tensors changed: MLP 0/264, Norms 0/425, Attention 208/424, Embeddings 0/5, other 0/1