Qwen
/

Qwen-14B-Chat-Int4

Text Generation

4-bit precision

Model card Files Files and versions Community

Qwen-14B-Chat-Int4 / configuration_qwen.py

Commit History

softmax_in_fp32

6c6ec1c

yangapku commited on Sep 28, 2023

update kvcache

a828abf

yangapku commited on Sep 25, 2023

upload model

ac4ce9b

yangapku commited on Sep 24, 2023