Nickyang/Hy3-RAZOR-226B-A21B-E144of192
LoRA-style vs tencent/Hy3. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, up_proj changed, in 80 of 81 layers; norms, biases and embeddings are untouched.
Tensors changed: MLP 1493/1768, Attention 0/324, lm_head 0/1, other 0/1, Norms 0/328, Embeddings 0/1