fumetodev/Hy-MT2-1.8B-JP-Manga-Finetune-chinese-zh-Hans-v1-GGUF
LoRA-style vs tencent/Hy-MT2-1.8B. 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 96/96, Attention 128/128