Commit History

update modeling_qwen.py
348227b

yangapku commited on

update modeling_qwen.py
68600f4

yangapku commited on

update modeling_qwen.py
f2191b9

yangapku commited on

update modeling_qwen.py
1e66ba4

yangapku commited on

update
5ff8f11

yangapku commited on

remove fix-sized causal mask
c02ede5

yangapku commited on

update wechat.png
ea58180

yangapku commited on

add kernel file check in modeling_qwen.py
5bfdae9

yangapku commited on

update modeling.py
8750247

yangapku commited on

update int8 quantization info
95590fa

yangapku commited on

update modeling_qwen.py
6ec2d41

yangapku commited on

update batch inference
246a75e

yangapku commited on

update default generate hyperparams
a3c216d

yangapku commited on

format
02fc63b

yangapku commited on

update tokenization.py
aa4c54a

yangapku commited on

update tokenization.py
c70791d

yangapku commited on

Update README.md
b725fe5

yangapku commited on

Update README.md
0e4b3b8

yangapku commited on

softmax_in_fp32
682f4da

yangapku commited on

update modeling_qwen.py
f6d1017

yangapku commited on

update kernels
1581be8

yangapku commited on

update modeling_qwen.py
fcc99d6

yangapku commited on

update modeling_qwen.py
f4b568f

yangapku commited on

Upload 2 files
3b3a62f

yangapku commited on

Upload code_interpreter_showcase_001.jpg
f4934ae

yangapku commited on

update kvcache
0e3568a

yangapku commited on

update readme
8afa075

yangapku commited on

update model
ff5200f

yangapku commited on