profile-img
Robert Dadashi

@robdadashi

reinforcement learning research @GoogleDeepMind, built RLHF layer of Bard and Gemma

calendar_today09-09-2014 13:30:01

121 Tweets

1,5K Followers

389 Following

Robert Dadashi(@robdadashi) 's Twitter Profile Photo
Robert Dadashi
@robdadashi

3 weeks ago

I am very happy to announce that Gemma 1.1 Instruct 2B and “7B” are out! Here are a few details about the new models:
1/11

account_circle