Commit History

support cpu inference, fix conflicts between fp32 and flash-attn

9f94ac2

JustinLin610 commited on Aug 4, 2023

fix decoder, and provide an option to remove attack rejection (#8)

f6498e5

JustinLin610 commited on Aug 4, 2023

Update Readme.md, fix typo

62bf1c6

logicwong commited on Aug 4, 2023

Update modeling_qwen.py, fix logn bug

f157e4e

logicwong commited on Aug 4, 2023

fix overflow

da187eb

JustinLin610 commited on Aug 4, 2023

Update config.json

4e41480

logicwong commited on Aug 4, 2023

update fast usage

44e46a0

yangapku commited on Aug 3, 2023

update humaneval score

d0db884

yangapku commited on Aug 3, 2023

update fast usage

f59a0a9

yangapku commited on Aug 3, 2023

Upload wanx_colorful_black.png

e03d77d

majx13 commited on Aug 3, 2023

implement _convert_id_to_token

10173d4

yangapku commited on Aug 3, 2023

fix flash-attention usage

405556d

yangapku commited on Aug 3, 2023

Update README.md

1a2571e

yangapku commited on Aug 3, 2023

update tokenization_qwen.py

3f9f12c

yangapku commited on Aug 3, 2023

fix report link

5e7f6a3

yangapku commited on Aug 3, 2023

update demo link

09644a4

yangapku commited on Aug 3, 2023

update tokenization_qwen.py

9882935

yangapku commited on Aug 3, 2023

update react example

8504b36

yangapku commited on Aug 3, 2023

disable hosted inference API

946cbc6

yangapku commited on Aug 3, 2023

update readme

9f47669

yangapku commited on Aug 3, 2023

add resource files

4658aaa

yangapku commited on Aug 3, 2023

upload pytorch_model.bin

498baa4

yangapku commited on Aug 3, 2023

Create README.md

55ab57f

yangapku commited on Aug 3, 2023

initial commit

bfbac77

yangapku commited on Aug 3, 2023

Commit History

support cpu inference, fix conflicts between fp32 and flash-attn 9f94ac2

fix decoder, and provide an option to remove attack rejection (#8) f6498e5

Update Readme.md, fix typo 62bf1c6

Update modeling_qwen.py, fix logn bug f157e4e

fix overflow da187eb

Update config.json 4e41480

update fast usage 44e46a0

update humaneval score d0db884

update fast usage f59a0a9

Upload wanx_colorful_black.png e03d77d

implement _convert_id_to_token 10173d4

fix flash-attention usage 405556d

Update README.md 1a2571e

update tokenization_qwen.py 3f9f12c

fix report link 5e7f6a3

update demo link 09644a4

update tokenization_qwen.py 9882935

update react example 8504b36

disable hosted inference API 946cbc6

update readme 9f47669

add resource files 4658aaa

upload pytorch_model.bin 498baa4

Create README.md 55ab57f

initial commit bfbac77

support cpu inference, fix conflicts between fp32 and flash-attn

9f94ac2

fix decoder, and provide an option to remove attack rejection (#8)

f6498e5

Update Readme.md, fix typo

62bf1c6

Update modeling_qwen.py, fix logn bug

f157e4e

fix overflow

da187eb

Update config.json

4e41480

update fast usage

44e46a0

update humaneval score

d0db884

update fast usage

f59a0a9

Upload wanx_colorful_black.png

e03d77d

implement _convert_id_to_token

10173d4

fix flash-attention usage

405556d

Update README.md

1a2571e

update tokenization_qwen.py

3f9f12c

fix report link

5e7f6a3

update demo link

09644a4

update tokenization_qwen.py

9882935

update react example

8504b36

disable hosted inference API

946cbc6

update readme

9f47669

add resource files

4658aaa

upload pytorch_model.bin

498baa4

Create README.md

55ab57f

initial commit

bfbac77