Qwen
/

Qwen-14B-Chat-Int8

Text Generation

8-bit precision

Model card Files Files and versions Community

Qwen-14B-Chat-Int8

Commit History

remove fix-sized causal mask

166eb67

yangapku commited on Nov 14, 2023

update wechat.png

f5b2308

yangapku commited on Nov 14, 2023

add kernel file check in modeling_qwen.py

5ef07ce

yangapku commited on Nov 5, 2023

update modeling.py

1a3186c

yangapku commited on Oct 26, 2023

Upload 3 files

a71f91b

yangapku commited on Oct 17, 2023

update int8 quantization info

4bf9d82

yangapku commited on Oct 17, 2023

update modeling_qwen.py

6ca42df

yangapku commited on Oct 16, 2023

update batch inference

7f8da63

yangapku commited on Oct 14, 2023

update default generate hyperparams

6bd1a5a

yangapku commited on Oct 13, 2023

upload model

9a3c8fc

yangapku commited on Oct 12, 2023

initial commit

20f510e

yangapku commited on Oct 12, 2023