We've fine-tuned GPT-2 using human feedback for tasks such as summarizing articles, matching the preferences of human labelers (if not always our own). We're hoping this brings safety methods closer to machines learning values by talking with humans.https://openai.com/blog/fine-tuning-gpt-2/ …
Odgovor korisniku/ci @OpenAI
Such a cool update to GPT-2. What I like about this is the qualitative examples showing improvement. So much better than “we’ve beat the SOTA by 0.01%”
14:18 - 19. ruj 2019.
0 replies
0 proslijeđenih tweetova
4 korisnika označavaju da im se sviđa
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.