File size: 298 Bytes
b05f831 a4dbeee b05f831 ededf3e |
1 2 3 4 5 6 7 8 9 10 11 |
---
license: apache-2.0
tags:
- 2bit
- llama
- XVERSE
---
You can run it on 2G mem GPU,quantize base QuIP# method, a weights-only quantization method that is able to achieve near fp16 performance using only 2 bits per weight.
url:https://github.com/Cornell-RelaxML/quip-sharp/tree/release20231203 |