Contributor Spotlight: Mohammad Aflah Khan
Mohammad Aflah Khan on his background and contributions to EleutherAI.
EleutherAI's Research Blog
Previous Posts
The first New England RLHF Hackers Hackathon
Introduction Author list is alphabetical by last name. We would like to extend acknowledgements to Delta Christine Hessler and Hailey Schoelkopf. On September 10, 2023, New England RLHF Hackers (NERH) held a hackathon at …
EleutherAI's Thoughts on the EU AI Act
How we are supporting open source and open science in the EU AI Act.
Minetester: A fully open RL environment built on Minetest
An overview of Minetester and preliminary work
🐶Safetensors audited as really safe and becoming the default
Audit shows that safetensors is safe and ready to become the default Hugging Face, in close collaboration with EleutherAI and Stability AI, has ordered an external security audit of the safetensors library, the results …
Alignment Research @ EleutherAI
A brief overview of EleutherAI's approach to alignment
Transformer Math 101
We present basic math related to computation and memory usage for transformers
Exploratory Analysis of TRLX RLHF Transformers with TransformerLens
A demonstration of interpretability for RLHF models
EleutherAI Second Retrospective: The long version
What we've been up to for the past year-and-a-half at EleutherAI.
The View from 30,000 Feet: Preface to the Second EleutherAI Retrospective
(Some of) what we've been up to for the past year-and-a-half at EleutherAI.
Announcing GPT-NeoX-20B
Announcing GPT-NeoX-20B, a 20 billion parameter model trained in collaboration with CoreWeave.
A Preliminary Exploration into Factored Cognition with Language Models
Exploring factored cognition by decomposing arithmetic tasks for GPT-3.
Multiple Choice Normalization in LM Evaluation
There are multiple ways of evaluating multiple-choice tasks on autoregressive language models like GPT-3/Neo/J. This post lays out the current prevalent normalization methods.
Downstream Evaluations of Rotary Position Embeddings
A comparison of Rotary Position Embedding against GPT-style learned position embeddings.
What A Long, Strange Trip It's Been: EleutherAI One Year Retrospective
A look back at the first year of EleutherAI.