Praha-Labs/LFM-MALAYALAM-TTS-v0.1

Full fine-tune vs LiquidAI/LFM2-350M. Fine-tune: 100% of the weights changed, across 16 of 16 layers.

Tensors changed: Embeddings 1/1, other 30/30, MLP 48/48, Norms 44/44, Attention 24/24

2 derivatives checked

• mradermacher/LFM-MALAYALAM-TTS-V2-GGUF: Same weights, converted
• mradermacher/LFM-MALAYALAM-TTS-v0.1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse