aguken-ai/Qwen-3-TTS-12Hz-0.6B-Base-hi-LoRA-Finetuned-BNB-NF4
LoRA-style vs Qwen/Qwen3-TTS-12Hz-0.6B-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: other 0/77, lm_head 0/15, Embeddings 0/17, Norms 0/134, MLP 99/103, Attention 132/132