Hugging Face's logo

Qwen
/
Qwen-14B-Chat-Int4

Text Generation
Transformers
Safetensors
Chinese
English
qwen
custom_code
4-bit precision
gptq
Model card Files Community
9
Qwen-14B-Chat-Int4 / modeling_qwen.py

Commit History

remove fix-sized causal mask
6e72378

yangapku commited on

add kernel file check in modeling_qwen.py
0374c21

yangapku commited on

update modeling.py
f5e4b21

yangapku commited on

update modeling_qwen.py
5d28542

yangapku commited on

update batch inference
4b4dcdc

yangapku commited on

softmax_in_fp32
6c6ec1c

yangapku commited on

update modeling_qwen.py
5d52159

yangapku commited on

update kernels
b980709

yangapku commited on

update modeling_qwen.py
45eb93c

yangapku commited on

update modeling_qwen.py
0f5e18f

yangapku commited on

update kvcache
a828abf

yangapku commited on

update readme
f47dcd2

yangapku commited on

update batch infer
d83208a

yangapku commited on

upload model
ac4ce9b

yangapku commited on