notmax123/QwenTTS-he-1.7B
Adapter vs Qwen/Qwen3-TTS-12Hz-1.7B-Base. notmax123/QwenTTS-he-1.7B is a LoRA adapter, not full weights: rank 32, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 28 layers (231 adapted matrices). It modifies Qwen/Qwen3-TTS-12Hz-1.7B-Base at load time.