malaysia-ai/Qwen3-1.7B-Multilingual-TTS
Full fine-tune vs Qwen/Qwen3-1.7B-Base. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 109/113, MLP 84/84, Attention 112/112
2 derivatives checked
- mradermacher/Qwen3-1.7B-Multilingual-TTS-GGUF: Full fine-tune
- marafx2007/Qwen3-1.7B-Multilingual-TTS-GGUF: Full fine-tune