This is 2-bit quantization of Qwen/Qwen1.5-72B-Chat using QuIP#
Random samples from RedPajama and Skypile (for Chinese) are used as calibration data.
Model loading
Please follow the instruction of QuIP-for-all for usage.
As an alternative, you can use Aphrodite engine or my vLLM branch for faster inference. If you have problem installing fast-hadamard-transform
from pip, you can also install it from source
- Downloads last month
- 3
Inference API (serverless) is not available, repository is disabled.