overfeed.news

Fine-tuning GPT-2 from human preferences

OpenAI Newsen

6a

Idade

Publicado
Coletado

We’ve fine-tuned the 774M parameter GPT-2 language model using human feedback for various tasks, successfully matching the preferences of the external human labelers, though those preferences did not always match our own. Specifically, for summarization tasks the labelers preferred sentences copied wholesale from the input (we’d only asked them to ensure accuracy), so our models learned to copy. Summarization required…

Leia o artigo completo em openai.com

O overfeed.news indexa e aponta. Publicamos um trecho curto — o artigo completo fica em OpenAI News.

Mais de OpenAI News

Entre para seguir esta fonte
Fine-tuning GPT-2 from human preferences — overfeed.news