Heegyu Kim PRO
heegyu
AI & ML interests
NLP
Recent Activity
liked
a model
23 minutes ago
MiniMaxAI/MiniMax-M2.1
upvoted
an
article
3 days ago
Deriving the PPO Loss from First Principles
liked
a dataset
7 days ago
KETI-AIR/kor_qasc
Organizations
Korean Datasets, Reward Models for RLHF
-
heegyu/KoSafeGuard-8b-0503
Text Generation • 8B • Updated • 37 • 5 -
heegyu/ko-reward-model-helpful-1.3b-v0.2
Text Classification • 1B • Updated • 11 -
heegyu/ko-reward-model-safety-1.3b-v0.2
Text Classification • 1B • Updated • 16 • 5 -
heegyu/ko-reward-model-helpful-roberta-large-v0.1
Text Classification • 0.3B • Updated • 17 • 2
AjouBlue-GPT: Small Korean Generative Language Models with 125M, 355M parameters
-
Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment
Paper • 2310.00212 • Published • 2 -
Stabilizing RLHF through Advantage Model and Selective Rehearsal
Paper • 2309.10202 • Published • 11 -
Aligning Language Models with Offline Reinforcement Learning from Human Feedback
Paper • 2308.12050 • Published • 1 -
Secrets of RLHF in Large Language Models Part I: PPO
Paper • 2307.04964 • Published • 29
Korean Datasets, Reward Models for RLHF
-
heegyu/KoSafeGuard-8b-0503
Text Generation • 8B • Updated • 37 • 5 -
heegyu/ko-reward-model-helpful-1.3b-v0.2
Text Classification • 1B • Updated • 11 -
heegyu/ko-reward-model-safety-1.3b-v0.2
Text Classification • 1B • Updated • 16 • 5 -
heegyu/ko-reward-model-helpful-roberta-large-v0.1
Text Classification • 0.3B • Updated • 17 • 2
AjouBlue-GPT: Small Korean Generative Language Models with 125M, 355M parameters
-
Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment
Paper • 2310.00212 • Published • 2 -
Stabilizing RLHF through Advantage Model and Selective Rehearsal
Paper • 2309.10202 • Published • 11 -
Aligning Language Models with Offline Reinforcement Learning from Human Feedback
Paper • 2308.12050 • Published • 1 -
Secrets of RLHF in Large Language Models Part I: PPO
Paper • 2307.04964 • Published • 29