cloudraker/rakedoc-nano
LoRA-style vs florin-inc/florin-parser-nano. 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 24 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, Norms 0/179, MLP 72/204, Attention 96/296