Michael N

mnoukhov's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

updated a model 23 days ago

mnoukhov/SmolLM2-135M-tldr-sft

Text Generation • Updated 23 days ago • 134

updated a model 3 months ago

mnoukhov/SmolLM2-360M-tldr-sft

Text Generation • Updated Nov 13, 2024 • 14

New activity in trl-lib/tldr 3 months ago

Extra space at start of completion

#2 opened 3 months ago by

mnoukhov

updated 2 models 3 months ago

mnoukhov/SmolLM2-135M-Instruct_tldr-sft

Text Generation • Updated Nov 12, 2024 • 17

mnoukhov/SmolLM2-135M-Instruct_tldr-rm

Text Classification • Updated Nov 11, 2024 • 111

updated a collection 3 months ago

Asynchronous RLHF

Collection

Models and datasets for asynchronous rlhf paper, see code at https://github.com/mnoukhov/async_rlhf • 10 items • Updated Oct 28, 2024

commented a paper 3 months ago

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

Paper • 2410.18252 • Published Oct 23, 2024 • 5 •

2

authored a paper 3 months ago

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

Paper • 2403.17031 • Published Mar 24, 2024 • 4

updated 2 collections 3 months ago

Asynchronous RLHF

Collection

Models and datasets for asynchronous rlhf paper, see code at https://github.com/mnoukhov/async_rlhf • 10 items • Updated Oct 28, 2024

Elastic Reset

Collection

Models and datasets for Elastic Reset (NeurIPS 2023), code at https://github.com/mnoukhov/elastic-reset • 5 items • Updated Oct 22, 2024