cstr/reazonspeech-nemo-v2-GGUF
0561
Requantize reazonspeech-nemo-v2-q8_0.gguf: conv pw1/pw2 F16→Q8_0 (#81 CPU perf fix; all other tensors byte-identical)
Requantize reazonspeech-nemo-v2-q4_k.gguf: conv pw1/pw2 F16→Q8_0 (#81 CPU perf fix; all other tensors byte-identical)
Add model card
Upload reazonspeech-nemo-v2-q4_k.gguf with huggingface_hub
Upload reazonspeech-nemo-v2-q8_0.gguf with huggingface_hub
Upload reazonspeech-nemo-v2-f16.gguf with huggingface_hub
initial commit
