DrRiceIO7/Franken-MoE-Small-SFT-Preview-v2
LoRA-style vs DrRiceIO7/Franken-MoE-Small-Base. 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 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 672/700, Attention 112/112