mradermacher/QOR-TTS-1.7B-GGUF
Same weights, converted (fewer layers) vs qoranet/QOR-TTS-1.7B. mradermacher/QOR-TTS-1.7B-GGUF matches part of qoranet/QOR-TTS-1.7B (309 of its 480 tensors; the rest of qoranet/QOR-TTS-1.7B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32), plus 2 new tensors.
Tensors changed: Norms 0/113, MLP 0/84, Attention 0/112