Lecture

Pretraining: Transformers & Models

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Description

This lecture explores the concept of pretraining models, focusing on the use of word embeddings and contextualized word representations for transfer learning. It covers key models like BERT, T5, and GPT, discussing their training objectives and applications. The lecture delves into the motivations behind model pretraining, the effectiveness of large models, and the benefits of in-context learning. It also examines the limitations of pretrained encoders, the extensions of BERT, and the advancements in parameter-efficient finetuning methods. Additionally, it discusses the pretraining of encoders and decoders, the GPT series, and the implications of very large language models like GPT-3.

Official source

Related concepts (32)

Large language model

A large language model (LLM) is a language model characterized by its large size. Their size is enabled by AI accelerators, which are able to process vast amounts of text data, mostly scraped from the Internet. The artificial neural networks which are built can contain from tens of millions and up to billions of weights and are (pre-)trained using self-supervised learning and semi-supervised learning. Transformer architecture contributed to faster training.

Generative pre-trained transformer

Generative pre-trained transformers (GPT) are a type of large language model (LLM) and a prominent framework for generative artificial intelligence. The first GPT was introduced in 2018 by OpenAI. GPT models are artificial neural networks that are based on the transformer architecture, pre-trained on large data sets of unlabelled text, and able to generate novel human-like content. As of 2023, most LLMs have these characteristics and are sometimes referred to broadly as GPTs.

Transformer (machine learning model)

A transformer is a deep learning architecture that relies on the parallel multi-head attention mechanism. The modern transformer was proposed in the 2017 paper titled 'Attention Is All You Need' by Ashish Vaswani et al., Google Brain team. It is notable for requiring less training time than previous recurrent neural architectures, such as long short-term memory (LSTM), and its later variation has been prevalently adopted for training large language models on large (language) datasets, such as the Wikipedia corpus and Common Crawl, by virtue of the parallelized processing of input sequence.

Language model

A language model is a probabilistic model of a natural language that can generate probabilities of a series of words, based on text corpora in one or multiple languages it was trained on. Large language models, as their most advanced form, are a combination of feedforward neural networks and transformers. They have superseded recurrent neural network-based models, which had previously superseded the pure statistical models, such as word n-gram language model.

Text-to-image model

A text-to-image model is a machine learning model which takes an input natural language description and produces an image matching that description. Such models began to be developed in the mid-2010s, as a result of advances in deep neural networks. In 2022, the output of state of the art text-to-image models, such as OpenAI's DALL-E 2, Google Brain's , StabilityAI's Stable Diffusion, and Midjourney began to approach the quality of real photographs and human-drawn art.

Related lectures (64)

Modern NLP: From GPT to ChatGPT

Explores the evolution of modern NLP from GPT-2 to GPT-3, emphasizing in-context learning and the development of ChatGPT.

Contextual Representations: ELMO and BERT Overview

Covers contextual representations in NLP, focusing on ELMO and BERT architectures and their applications in various tasks.

Prompting and Alignment

Explores prompting, alignment, and the capabilities of large language models for natural language processing tasks.

Language Models: From Theory to Computation

Explores the mathematics of language models, covering architecture design, pre-training, and fine-tuning, emphasizing the importance of pre-training and fine-tuning for various tasks.

Sequence to Sequence Models: Overview and Applications