theaviv/Lev1-3.7B
LoRA-style vs IFM/K2-Horizon-3.7B. 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 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/73, MLP 108/108, Attention 144/144, lm_head 0/1, Embeddings 0/1