explained

AI Deep Learning Large Language Models

Are Retentive Networks A Successor to Transformer for Large Language Models?

Retention is an alternative to Attention in Transformers that can both be written in a parallel and in a recurrent fashion. This means the architecture achieves training parallelism while maintaining low-cost inference. Experiments in the paper look very promising. Yannic Kilcher elaborates.

Read More
AI Large Language Models Research

Scaling Transformer to 1M tokens and beyond with RMT (Paper Explained)

Yannic Kilcher explains this paper that promises to scale transformers to 1 million tokens and beyond. We take a look at the technique behind it: The Recurrent Memory Transformer, and what its strengths and weaknesses are.

Read More
Natural Language Processing Research

LLaMA: Open and Efficient Foundation Language Models (Paper Explained)

Large Language Models (LLMs) are all the rage right now. ChatGPT is the LLM everyone talks about, but there are others. With the attention (and money) that OpenAI is getting, expect more of them. LLaMA is a series of large language models from 7B to 65B parameters, trained by Meta AI. They train for longer […]

Read More
AI Generative AI Natural Language Processing

ChatGPT: This AI has a JAILBREAK?!

Yannic explores ChatGPT and discovers that it has a JailBreak?! ChatGPT, OpenAI’s newest model is a GPT-3 variant that has been fine-tuned using Reinforcement Learning from Human Feedback, and it is taking the world by storm!

Read More
AI Natural Language Processing

ROME: Locating and Editing Factual Associations in GPT (Paper Explained & Author Interview)

Large Language Models have the ability to store vast amounts of facts about the world. But little is known, how these models actually do this. This paper aims at discovering the mechanism and location of storage and recall of factual associations in GPT models, and then proposes a mechanism for the targeted editing of such […]

Read More
AI Mathematics

This is a game changer! (AlphaTensor by DeepMind explained)

Matrix multiplication is the most used mathematical operation in all of science and engineering. Speeding this up has massive consequences. Thus, over the years, this operation has become more and more optimized. A fascinating discovery was made when it was shown that one actually needs less than N^3 multiplication operations to multiply to NxN matrices. […]

Read More