ASLP-lab/VoiceSculptor-VD

Full fine-tune vs HKUSTAudio/Llasa-3B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Norms 57/57, MLP 84/84, Attention 112/112

2 derivatives checked

• mradermacher/VoiceSculptor-VD-i1-GGUF: Quantization
• mradermacher/VoiceSculptor-VD-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse