dolly-vn/Vira-TTS
Full fine-tune vs Qwen/Qwen2-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 49/49, MLP 72/72, Attention 168/168
1 derivatives checked
- mradermacher/Vira-TTS-GGUF: Same weights, converted
Full fine-tune vs Qwen/Qwen2-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 49/49, MLP 72/72, Attention 168/168