raj-hitpromo/hit-promo-reasoner
LoRA-style vs microsoft/Phi-4-mini-reasoning. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_up_proj, o_proj, qkv_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 64/64, Attention 64/64