Aratako/MioTTS-2.6B
Full fine-tune vs LiquidAI/LFM2-2.6B. Fine-tune: 99% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 1/1, other 65/66, MLP 90/90, Norms 75/76, Attention 32/32
Full fine-tune vs LiquidAI/LFM2-2.6B. Fine-tune: 99% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 1/1, other 65/66, MLP 90/90, Norms 75/76, Attention 32/32