williamlcn/17718_simpo_32_16_05e_0317
LoRA-style vs williamlcn/17718_sft_32_sh_0317. 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 26 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/105, MLP 0/78, Attention 104/104