Code Refinement Project

Code-Refinement's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

mnoukhov 

submitted a paper to Daily Papers 3 days ago

Learning to Solve Hard Problems in RL for LLMs by Never Giving Up

Paper • 2609.13443 • Published 8 days ago • 10

nikishin 

authored a paper over 1 year ago

Forgetting Transformer: Softmax Attention with a Forget Gate

Paper • 2503.02130 • Published Mar 3, 2025 • 32

mnoukhov 

authored a paper almost 2 years ago

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

Paper • 2403.17031 • Published Mar 24, 2024 • 8

mnoukhov 

updated a model over 2 years ago

Code-Refinement/dpo-sample-perfect-more

Updated May 14, 2024

mnoukhov 

updated 2 datasets over 2 years ago

Code-Refinement/dpo-sample-perfect-more

Viewer • Updated May 14, 2024 • 128 • 21

Code-Refinement/dpo-sample-perfect-less

Viewer • Updated May 14, 2024 • 128 • 22 • 1

mnoukhov 

updated 9 models over 2 years ago

Code-Refinement/dpo_utf_20_refs_perfect-less_merged

Text Generation • 7B • Updated Mar 14, 2024 • 18

Code-Refinement/dpo_utf_20_refs_perfect-more_merged

Text Generation • 7B • Updated Mar 14, 2024 • 16

Code-Refinement/dpo_utf_20_refs_perfect-less

Updated Mar 13, 2024

Code-Refinement/dpo_utf_20_refs_max-less_merged

Text Generation • 7B • Updated Mar 13, 2024 • 15

Code-Refinement/dpo_utf_20_refs_max-more_merged

Text Generation • 7B • Updated Mar 13, 2024 • 15

Code-Refinement/dpo_utf_20_refs_perfect-more

Updated Mar 12, 2024

Code-Refinement/dpo_utf_20_refs_max-less

Updated Mar 8, 2024

Code-Refinement/dpo_utf_20_refs_max-more

Updated Mar 7, 2024

Code-Refinement/testmodel

Updated Mar 7, 2024

mnoukhov 

updated 4 datasets over 2 years ago

Code-Refinement/utf_20_refs_pairs

Viewer • Updated Feb 16, 2024 • 3.68k • 15

Code-Refinement/utf_20_refs_file

Viewer • Updated Feb 1, 2024 • 3.68k • 25

Code-Refinement/utf_20_refs_file_sample100

Viewer • Updated Feb 1, 2024 • 200 • 10

Code-Refinement/utf_20_refs

Viewer • Updated Jan 30, 2024 • 372k • 21

mnoukhov 

updated a model over 2 years ago

Code-Refinement/5_refs_utf_only

Updated Jan 11, 2024 • 7