Classifier-Free Guidance (CFG) has recently emerged in text-to-image
gen...
Concept erasure aims to remove specified features from a representation....
Noticing the urgent need to provide tools for fast and user-friendly
qua...
In recent years, self-attention has become the dominant paradigm for seq...
Neural networks have in recent years shown promise for helping software
...
Memorization, or the tendency of large language models (LLMs) to output
...
How do large language models (LLMs) develop and evolve over the course o...
We analyze transformers from the perspective of iterative inference, see...
As language models grow ever larger, the need for large-scale high-quali...
The BLOOM model is a large open-source multilingual language model capab...
Multitask prompted finetuning (MTF) has been shown to help large languag...
Despite widespread use of LLMs as conversational agents, evaluations of
...
Over the past two years, EleutherAI has established itself as a radicall...
The recent emergence and adoption of Machine Learning technology, and
sp...
Generating and editing images from open domain text prompts is a challen...
We introduce GPT-NeoX-20B, a 20 billion parameter autoregressive languag...
In recent years, large-scale data collection efforts have prioritized th...
As artificial intelligence (AI) technologies become increasingly powerfu...
This datasheet describes the Pile, a 825 GiB dataset of human-authored t...
Large language models have recently been shown to attain reasonable zero...
In this paper, we propose the beginnings of a formal framework for model...
With the success of large-scale pre-training and multilingual modeling i...
Recent work has demonstrated that increased training dataset diversity
i...
Machine learning has the potential to fuel further advances in data scie...
Magic: the Gathering is a popular and famously complicated card game abo...
Magic: The Gathering is a popular and famously complicated trading
card ...