cleanrl

non-profit

https://github.com/vwxyzjn/cleanrl

vwxyzjn

vwxyzjn

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

vwxyzjn authored a paper about 2 months ago

The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization

vwxyzjn authored a paper about 2 months ago

A2C is a special case of PPO

vwxyzjn authored a paper about 2 months ago

Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models

View all activity

models 1217

cleanrl/EleutherAI_pythia-6.9b-dedupedppotldr

Text Generation • Updated May 30, 2024 • 11

cleanrl/EleutherAI_pythia-2.8b-dedupedppotldr

Text Generation • Updated May 30, 2024 • 10

cleanrl/EleutherAI_pythia-1b-dedupedppotldr

Text Generation • Updated May 30, 2024 • 64

cleanrl/EleutherAI_pythia-2.8b-dedupedrewardtldr

Text Classification • Updated May 15, 2024 • 13

cleanrl/EleutherAI_pythia-1b-dedupedrewardtldr

Text Classification • Updated May 15, 2024 • 3.64k

cleanrl/EleutherAI_pythia-1b-dedupedsfttldr

Text Generation • Updated May 15, 2024 • 4.32k

cleanrl/EleutherAI_pythia-2.8b-dedupedsfttldr

Text Generation • Updated May 15, 2024 • 9

cleanrl/EleutherAI_pythia-6.9b-dedupedsfttldr

Text Generation • Updated May 15, 2024 • 73

cleanrl/EleutherAI_pythia-6.9b-dedupedrewardtldr

Text Classification • Updated May 7, 2024 • 106

cleanrl/ppo_zephyr310

Text Generation • Updated May 1, 2024 • 9

datasets 15

cleanrl/summarize_from_feedback_oai_preprocessing_1705009345

Viewer • Updated Jan 11, 2024 • 179k • 540

cleanrl/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1705009345

Viewer • Updated Jan 11, 2024 • 130k • 164

cleanrl/summarize_from_feedback_oai_preprocessing_1704578687

Viewer • Updated Jan 6, 2024 • 179k • 334

cleanrl/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1704578687

Viewer • Updated Jan 6, 2024 • 130k • 130

cleanrl/summarize_from_feedback_oai_preprocessing_1704563162

Viewer • Updated Jan 6, 2024 • 179k • 245

cleanrl/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1704563162

Viewer • Updated Jan 6, 2024 • 130k • 223

cleanrl/summarize_from_feedback_oai_preprocessing_1704496365

Viewer • Updated Jan 5, 2024 • 179k • 333

cleanrl/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1704496365

Viewer • Updated Jan 5, 2024 • 130k • 199

cleanrl/summarize_from_feedback_oai_preprocessing_1704427060

Viewer • Updated Jan 5, 2024 • 179k • 278

cleanrl/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1704427060

Viewer • Updated Jan 5, 2024 • 130k • 197