support cpu inference, format file

by JustinLin610 - opened Aug 4, 2023

base: refs/heads/main

←

from: refs/pr/9

Discussion Files changed

+712

-3870

initial commitbfbac778

Create README.md55ab57fb

upload pytorch_model.bin498baa46

add resource files4658aaa8

update readme9f476698

disable hosted inference API946cbc62

update react example8504b36b

update tokenization_qwen.py9882935f

update demo link09644a4f

fix report link5e7f6a3f

update tokenization_qwen.py3f9f12c5

Update README.md1a2571e8

fix flash-attention usage405556da

implement _convert_id_to_token10173d49

Upload wanx_colorful_black.pnge03d77d8

update fast usagef59a0a94

update humaneval scored0db884e

update fast usage44e46a0f

Update config.json4e41480b

fix overflowda187eb5

Update modeling_qwen.py, fix logn bugf157e4e5

Update Readme.md, fix typo62bf1c62

fix decoder, and provide an option to remove attack rejection (#8)f6498e5d

JustinLin610

Qwen org Aug 4, 2023

No description provided.

support cpu inference, fix conflicts between fp32 and flash-attn9f94ac27

JustinLin610 changed pull request title from support cpu inference, fix conflicts between fp32 and flash-attn to support cpu inference, format file Aug 4, 2023

JustinLin610 changed pull request status to merged Aug 4, 2023

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment