Hugging Face's logo
Wei Xiong's picture
13 11 19

Wei Xiong

weqweasdas
dangkai-nk's profile picture chengcheng22's profile picture chrisliu298's profile picture
·
https://weixiongust.github.io/WeiXiongUST/index.html

AI & ML interests

Machine learning, RLHF

Recent Activity

commented on a paper about 17 hours ago
Self-rewarding correction for mathematical reasoning
commented on a paper about 17 hours ago
Self-rewarding correction for mathematical reasoning
upvoted a paper about 22 hours ago
Self-rewarding correction for mathematical reasoning
View all activity

Organizations

reward modeling's profile picture raft_study's profile picture Directional Preference Alignment's profile picture RLHFlow's profile picture RRLHF's profile picture TIRData's profile picture feedbackagent's profile picture myselfrew's profile picture selfcorrexp's profile picture selfcorrexp2's profile picture mytestdpo's profile picture tmpmodelsave's profile picture qwselfcorr's profile picture dsrtrain's profile picture dsrselfcorr's profile picture

weqweasdas's activity

commented 2 papers about 17 hours ago
commented a paper about 22 hours ago
New activity in RLHFlow/LLaMA3-SFT 5 months ago

LLaMA3.1-SFT

3
#3 opened 5 months ago by
jackzhang
New activity in Qwen/Qwen2.5-Math-RM-72B 5 months ago

example to service the RM

1
#2 opened 5 months ago by
weqweasdas
New activity in RLHFlow/LLaMA3-SFT 6 months ago

How to use llama 3sft model, pipeline or tokenizer.apply_chat_template. Can you provide a simple example? Thank you very much for your contribution

2
#2 opened 6 months ago by
ZHIYII
New activity in RLHFlow/LLaMA3-SFT 7 months ago

Missing BOS token in tokenized text

2
#1 opened 7 months ago by
ZhaofengWu
New activity in RLHF4MATH/Gemma-7B-it-SFT3epoch 7 months ago

Update README.md
#1 opened 7 months ago by
weqweasdas
New activity in RLHFlow/ArmoRM-Llama3-8B-v0.1 7 months ago

Special tokens in the vocabulary?

4
#13 opened 7 months ago by
nshen7
New activity in sfairXC/FsfairX-LLaMA3-RM-v0.1 8 months ago

TypeError: Got unsupported ScalarType BFloat16

1
#5 opened 8 months ago by
AIR-hl
New activity in RLHFlow/pair-preference-model-LLaMA3-8B 8 months ago

Could you please test the consistency of preference between `RLHFlow/pair-preference-model-LLaMA3-8B` and GPT-4 on alpacaeval dataset?

1
#2 opened 8 months ago by
rungao2001
commented a paper 10 months ago
New activity in weqweasdas/RM-Mistral-7B 10 months ago

why vocab size is 32001

1
#3 opened 10 months ago by
yechenzhi1
New activity in weqweasdas/RM-Mistral-7B 11 months ago

License

1
#2 opened 11 months ago by
ravir123

Fix dataset link
#1 opened 11 months ago by
ZennyKenny