mradermacher/Orpheus_3B_TTS_Bangla_V4-GGUF
Same weights, converted vs utshobs/Orpheus_3B_TTS_Bangla_V4. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112
Same weights, converted vs utshobs/Orpheus_3B_TTS_Bangla_V4. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112