2 results found Sort:

voidful
TextRL voidful
65
531
mit
11
Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)
nlg nlp rlhf gpt-2 gpt-3 chatgpt pytorch controlled-nlg language-model reinforcement-learning
Created 2021-03-18
70 commits to main branch, last one about a month ago
naver
gdc naver
22
117
other
10
Code accompanying our papers on the "Generative Distributional Control" framework
ai nlg nlp gpt3 gpt-2 fairness-ml controlled-nlg language-model machine-learning exponential-family information-geometry reinforcement-learning
Created 2021-03-05
12 commits to master branch, last one about a year ago