Code Refinement Project

university

AI & ML interests

None defined yet.

Recent Activity

mnoukhov submitted a paper 17 days ago

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

nikishin authored a paper over 1 year ago

Forgetting Transformer: Softmax Attention with a Forget Gate

mnoukhov authored a paper almost 2 years ago

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

View all activity

models 11

Code-Refinement/dpo-sample-perfect-more

Updated May 14, 2024

Code-Refinement/dpo_utf_20_refs_perfect-less_merged

Text Generation • 7B • Updated Mar 14, 2024 • 21

Code-Refinement/dpo_utf_20_refs_perfect-more_merged

Text Generation • 7B • Updated Mar 14, 2024 • 21

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 • 21

Code-Refinement/dpo_utf_20_refs_max-more_merged

Text Generation • 7B • Updated Mar 13, 2024 • 20

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

datasets 6

Code-Refinement/dpo-sample-perfect-more

Viewer • Updated May 14, 2024 • 128 • 16

Code-Refinement/dpo-sample-perfect-less

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

Code-Refinement/utf_20_refs_pairs

Viewer • Updated Feb 16, 2024 • 3.68k • 19

Code-Refinement/utf_20_refs_file

Viewer • Updated Feb 1, 2024 • 3.68k • 17

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 • 36