Michael N's picture

3

Michael N

mnoukhov

·

http://mnoukhov.github.io

AI & ML interests

Representation learning for functional language

Recent Activity

published a model 23 days ago

mnoukhov/test

updated a model 2 months ago

mnoukhov/SmolLM2-135M-tldr-sft

updated a model 4 months ago

mnoukhov/SmolLM2-360M-tldr-sft

View all activity

Organizations

mnoukhov's activity

New activity in trl-lib/tldr 4 months ago

Extra space at start of completion

#2 opened 4 months ago by

commented a paper 5 months ago

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

Paper • 2410.18252 • Published Oct 23, 2024 • 7 •

New activity in arianhosseini/pythia410m-tldr-dpo-1b-relbl-10k over 1 year ago

change to correct base model

#1 opened over 1 year ago by