Michael Yang 06b31e2e24 quantize any fp16/fp32 model
- FROM /path/to/{safetensors,pytorch}
- FROM /path/to/fp{16,32}.bin
- FROM model:fp{16,32}
2024-05-03 13:18:28 -07:00
..
2024-05-03 13:18:28 -07:00