Third-party evaluation to identify risks in LLMs’ training data
A demonstration of third-party evaluation of private language-model training data using PySyft.
Announcement
Minetester: A fully open RL environment built on Minetest
An overview of Minetester and preliminary work
Alignment Research @ EleutherAI
A brief overview of EleutherAI's approach to alignment
Exploratory Analysis of TRLX RLHF Transformers with TransformerLens
A demonstration of interpretability for RLHF models
Announcing GPT-NeoX-20B
Announcing GPT-NeoX-20B, a 20 billion parameter model trained in collaboration with CoreWeave.