longtermrisk/Llama-3.1-8B-german-city-names-second-third-v2-sft-seed3-epoch3
LoRA-style vs unsloth/Meta-Llama-3.1-8B-Instruct. 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, v_proj changed, in 10 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 30/96, Attention 40/128, lm_head 0/1