Wei Xiong

weqweasdas's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented a paper 3 months ago

Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training

Paper • 2510.04996 • Published Oct 6, 2025 • 15 •

2

commented 2 papers 9 months ago

A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce

Paper • 2504.11343 • Published Apr 15, 2025 • 19 •

6

A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce

Paper • 2504.11343 • Published Apr 15, 2025 • 19 •

6

commented 4 papers 10 months ago

Self-rewarding correction for mathematical reasoning

Paper • 2502.19613 • Published Feb 26, 2025 • 82 •

6

Self-rewarding correction for mathematical reasoning

Paper • 2502.19613 • Published Feb 26, 2025 • 82 •

6

Self-rewarding correction for mathematical reasoning

Paper • 2502.19613 • Published Feb 26, 2025 • 82 •

6

Self-rewarding correction for mathematical reasoning

Paper • 2502.19613 • Published Feb 26, 2025 • 82 •

6

New activity in RLHFlow/LLaMA3-SFT over 1 year ago

LLaMA3.1-SFT

3

#3 opened over 1 year ago by

jackzhang

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 over 1 year ago by

ZHIYII

Missing BOS token in tokenized text

2

#1 opened over 1 year ago by

ZhaofengWu

New activity in RLHFlow/ArmoRM-Llama3-8B-v0.1 over 1 year ago

Special tokens in the vocabulary?

4

#13 opened over 1 year ago by

nshen7

New activity in sfairXC/FsfairX-LLaMA3-RM-v0.1 over 1 year ago

TypeError: Got unsupported ScalarType BFloat16

1

#5 opened over 1 year ago by

AIR-hl

New activity in RLHFlow/pair-preference-model-LLaMA3-8B over 1 year 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 over 1 year ago by

rungao2001

commented a paper over 1 year ago

RLHF Workflow: From Reward Modeling to Online RLHF

Paper • 2405.07863 • Published May 13, 2024 • 71 •

5

New activity in weqweasdas/RM-Mistral-7B over 1 year ago

why vocab size is 32001

1

#3 opened over 1 year ago by

yechenzhi1

License

1

#2 opened over 1 year ago by

ravir123

New activity in weqweasdas/RM-Mistral-7B almost 2 years ago

Fix dataset link

#1 opened almost 2 years ago by

ZennyKenny