AI / ML / LLM / Transformer Models Timeline Details

Viktor Garske @vemgar, Last update: Sun Jul 30 16:20:21 2023
← Back to the full graph

Helpful and Harmless

This graph is clickable!

timeline 04/2022 04/2022 05/2023 05/2023 04/2022->05/2023 Mpt7bInstruct MPT-7B-Instruct Mpt7bChat MPT-7B-Chat HhRlhf Helpful and Harmless HhRlhf->Mpt7bInstruct HhRlhf->Mpt7bChat
Type
Dataset
Paper name
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Paper authors
Bai et al.
Paper link
https://arxiv.org/abs/2204.05862
Publish date
2022-04-12
Affiliation
Anthropic