Hugging Face's logo
Shijie Wu's picture
16 7

Shijie Wu

shijie-wu
21world's profile picture
·

AI & ML interests

Large language model and multilinguality

Organizations

Bloomberg's profile picture Center for Language and Speech Processing @ JHU's profile picture

shijie-wu's activity

commented a paper over 1 year ago
New activity in jhu-clsp/roberta-large-eng-ara-128k over 1 year ago

Adding `safetensors` variant of this model
#2 opened over 1 year ago by
SFconvertbot
New activity in mosaicml/mpt-7b over 1 year ago

Using `self.transformer.wte.weight` directly for LM head breaks HF accelerate device map auto infer on multi-gpu

3
#46 opened over 1 year ago by
shijie-wu

Support device_map="auto" when loading

19
#23 opened over 1 year ago by
shijie-wu

Create requirements.txt

2
#22 opened over 1 year ago by
shijie-wu
New activity in jhu-clsp/bernice over 1 year ago

Adding `safetensors` variant of this model
#1 opened almost 2 years ago by
SFconvertbot
New activity in jhu-clsp/roberta-large-eng-ara-128k almost 2 years ago

Add multilingual to the language tag
#1 opened almost 2 years ago by
lbourdois
New activity in facebook/opt-125m over 2 years ago

Remove unused `activation_dropout`
#19 opened over 2 years ago by
shijie-wu
New activity in facebook/opt-350m over 2 years ago

Remove unused `activation_dropout`
#5 opened over 2 years ago by
shijie-wu
New activity in facebook/opt-1.3b over 2 years ago

Remove unused `activation_dropout`
#7 opened over 2 years ago by
shijie-wu
New activity in facebook/opt-2.7b over 2 years ago

Remove unused `activation_dropout`
#5 opened over 2 years ago by
shijie-wu
New activity in facebook/opt-6.7b over 2 years ago

Remove unused `activation_dropout`
#8 opened over 2 years ago by
shijie-wu
New activity in facebook/opt-30b over 2 years ago

Remove unused `activation_dropout`
#8 opened over 2 years ago by
shijie-wu
New activity in facebook/opt-66b over 2 years ago

Remove unused `activation_dropout`
#7 opened over 2 years ago by
shijie-wu
New activity in facebook/opt-13b over 2 years ago

Remove unused `activation_dropout`
#7 opened over 2 years ago by
shijie-wu
New activity in EleutherAI/gpt-neox-20b over 2 years ago

Fix eos_token_id
#3 opened over 2 years ago by
shijie-wu