calcuis/higgs-gguf

Same weights, converted vs bosonai/higgs-tts-2-3b-base. Same weights stored in another dtype (BF16 → F16), plus 3 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/168, Attention 0/112

On the Hub · Downloads on Model Pulse