GPT-1

Last updated
Generative Pre-trained Transformer 1 (GPT-1)
Original author(s) OpenAI
Initial releaseJune 2018;5 years ago (June 2018)
Repository
Successor GPT-2
Type
License MIT [1]
Website openai.com/blog/language-unsupervised/   OOjs UI icon edit-ltr-progressive.svg
Original GPT architecture Full GPT architecture.svg
Original GPT architecture

Generative Pre-trained Transformer 1 (GPT-1) was the first of OpenAI's large language models following Google's invention of the transformer architecture in 2017. [2] In June 2018, OpenAI released a paper entitled "Improving Language Understanding by Generative Pre-Training", [3] in which they introduced that initial model along with the general concept of a generative pre-trained transformer. [4]

Contents

Up to that point, the best-performing neural NLP models primarily employed supervised learning from large amounts of manually labeled data. This reliance on supervised learning limited their use of datasets that were not well-annotated, in addition to making it prohibitively expensive and time-consuming to train extremely large models; [3] [5] many languages (such as Swahili or Haitian Creole) are difficult to translate and interpret using such models due to a lack of available text for corpus-building. [5] In contrast, a GPT's "semi-supervised" approach involved two stages: an unsupervised generative "pre-training" stage in which a language modeling objective was used to set initial parameters, and a supervised discriminative "fine-tuning" stage in which these parameters were adapted to a target task. [3]

The use of a transformer architecture, as opposed to previous techniques involving attention-augmented RNNs, provided GPT models with a more structured memory than could be achieved through recurrent mechanisms; this resulted in "robust transfer performance across diverse tasks". [3]

Reason for choosing BookCorpus

BookCorpus was chosen as a training dataset partly because the long passages of continuous text helped the model learn to handle long-range information. [6] It contained over 7,000 unpublished fiction books from various genres. The rest of the datasets available at the time, while being larger, lacked this long-range structure (being "shuffled" at a sentence level). [3]

The BookCorpus text was cleaned by the ftfy library to standardized punctuation and whitespace and then tokenized by spaCy. [3]

Architecture

The GPT-1 architecture was a twelve-layer decoder-only transformer, using twelve masked self-attention heads, with 64-dimensional states each (for a total of 768). Rather than simple stochastic gradient descent, the Adam optimization algorithm was used; the learning rate was increased linearly from zero over the first 2,000 updates to a maximum of 2.5×10−4, and annealed to 0 using a cosine schedule. [3] GPT-1 has 117 million parameters. [4]

While the fine-tuning was adapted to specific tasks, its pre-training was not; to perform the various tasks, minimal changes were performed to its underlying task-agnostic model architecture. [3] Despite this, GPT-1 still improved on previous benchmarks in several language processing tasks, outperforming discriminatively-trained models with task-oriented architectures on several diverse tasks. [3]

Performance and evaluation

GPT-1 achieved a 5.8% and 1.5% improvement over previous best results [3] on natural language inference (also known as textual entailment ) tasks, evaluating the ability to interpret pairs of sentences from various datasets and classify the relationship between them as "entailment", "contradiction" or "neutral". [3] Examples of such datasets include QNLI (Wikipedia articles) and MultiNLI (transcribed speech, popular fiction, and government reports, among other sources); [7] It similarly outperformed previous models on two tasks related to question answering and commonsense reasoning—by 5.7% on RACE, [8] a dataset of written question-answer pairs from middle and high school exams, and by 8.9% on the Story Cloze Test. [9]

GPT-1 improved on previous best-performing models by 4.2% on semantic similarity (or paraphrase detection), evaluating the ability to predict whether two sentences are paraphrases of one another, using the Quora Question Pairs (QQP) dataset. [3]

GPT-1 achieved a score of 45.4, versus a previous best of 35.0 [3] in a text classification task using the Corpus of Linguistic Acceptability (CoLA). Finally, GPT-1 achieved an overall score of 72.8 (compared to a previous record of 68.9) on GLUE, a multi-task test. [10]

Related Research Articles

In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day. These assumptions include judgments about the nature of physical objects, taxonomic properties, and peoples' intentions. A device that exhibits commonsense reasoning might be capable of drawing conclusions that are similar to humans' folk psychology and naive physics.

A language model is a probabilistic model of a natural language. In 1980, the first significant statistical language model was proposed, and during the decade IBM performed ‘Shannon-style’ experiments, in which potential sources for language modeling improvement were identified by observing and analyzing the performance of human subjects in predicting or correcting text.

In natural language processing, textual entailment (TE), also known as natural language inference (NLI), is a directional relation between text fragments. The relation holds whenever the truth of one text fragment follows from another text.

<span class="mw-page-title-main">Feature learning</span> Set of learning techniques in machine learning

In machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task.

The Winograd schema challenge (WSC) is a test of machine intelligence proposed in 2012 by Hector Levesque, a computer scientist at the University of Toronto. Designed to be an improvement on the Turing test, it is a multiple-choice test that employs questions of a very specific structure: they are instances of what are called Winograd schemas, named after Terry Winograd, professor of computer science at Stanford University.

Neural machine translation (NMT) is an approach to machine translation that uses an artificial neural network to predict the likelihood of a sequence of words, typically modeling entire sentences in a single integrated model.

<span class="mw-page-title-main">Transformer (deep learning architecture)</span> Machine learning algorithm used for natural-language processing

A transformer is a deep learning architecture developed by Google and based on the multi-head attention mechanism, proposed in a 2017 paper "Attention Is All You Need". It has no recurrent units, and thus requires 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 (LLM) on large (language) datasets, such as the Wikipedia corpus and Common Crawl. Text is converted to numerical representations called tokens, and each token is converted into a vector via looking up from a word embedding table. At each layer, each token is then contextualized within the scope of the context window with other (unmasked) tokens via a parallel multi-head attention mechanism allowing the signal for key tokens to be amplified and less important tokens to be diminished. The transformer paper, published in 2017, is based on the softmax-based attention mechanism proposed by Bahdanau et. al. in 2014 for machine translation, and the Fast Weight Controller, similar to a transformer, proposed in 1992.

Bidirectional Encoder Representations from Transformers (BERT) is a language model based on the transformer architecture, notable for its dramatic improvement over previous state of the art models. It was introduced in October 2018 by researchers at Google. A 2020 literature survey concluded that "in a little over a year, BERT has become a ubiquitous baseline in Natural Language Processing (NLP) experiments counting over 150 research publications analyzing and improving the model."

Generative Pre-trained Transformer 3 (GPT-3) is a large language model released by OpenAI in 2020. Like its predecessor, GPT-2, it is a decoder-only transformer model of deep neural network, which supersedes recurrence and convolution-based architectures with a technique known as "attention". This attention mechanism allows the model to selectively focus on segments of input text it predicts to be most relevant. It uses a 2048-tokens-long context, float16 (16-bit) precision, and a hitherto-unprecedented 175 billion parameters, requiring 350GB of storage space as each parameter takes 2 bytes of space, and has demonstrated strong "zero-shot" and "few-shot" learning abilities on many tasks.

<span class="mw-page-title-main">GPT-2</span> 2019 text-generating language model

Generative Pre-trained Transformer 2 (GPT-2) is a large language model by OpenAI and the second in their foundational series of GPT models. GPT-2 was pre-trained a dataset of 8 million web pages. It was partially released in February 2019, followed by full release of the 1.5-billion-parameter model on November 5, 2019.

<span class="mw-page-title-main">DALL-E</span> Image-generating deep-learning model

DALL·E, DALL·E 2, and DALL·E 3 are text-to-image models developed by OpenAI using deep learning methodologies to generate digital images from natural language descriptions, called "prompts."

A foundation model is a machine learning model that is trained on broad data such that it can be applied across a wide range of use cases. Foundation models have transformed artificial intelligence (AI), powering prominent generative AI applications like ChatGPT. The Stanford Institute for Human-Centered Artificial Intelligence's Center for Research on Foundation Models created and popularized the term.

Generative Pre-trained Transformer 4 (GPT-4) is a multimodal large language model created by OpenAI, and the fourth in its series of GPT foundation models. It was launched on March 14, 2023, and made publicly available via the paid chatbot product ChatGPT Plus, via OpenAI's API, and via the free chatbot Microsoft Copilot. As a transformer-based model, GPT-4 uses a paradigm where pre-training using both public data and "data licensed from third-party providers" is used to predict the next token. After this step, the model was then fine-tuned with reinforcement learning feedback from humans and AI for human alignment and policy compliance.

<span class="mw-page-title-main">Generative pre-trained transformer</span> Type of large language model

Generative pre-trained transformers (GPT) are a type of large language model (LLM) and a prominent framework for generative artificial intelligence. They are artificial neural networks that are used in natural language processing tasks. GPTs 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.

<span class="mw-page-title-main">GPT-J</span> Open source artificial intelligence text generating language model developed by EleutherAI

GPT-J or GPT-J-6B is an open-source large language model (LLM) developed by EleutherAI in 2021. As the name suggests, it is a generative pre-trained transformer model designed to produce human-like text that continues from a prompt. The optional "6B" in the name refers to the fact that it has 6 billion parameters.

A large language model (LLM) is a language model notable for its ability to achieve general-purpose language generation and other natural language processing tasks such as classification. LLMs acquire these abilities by learning statistical relationships from text documents during a computationally intensive self-supervised and semi-supervised training process. LLMs can be used for text generation, a form of generative AI, by taking an input text and repeatedly predicting the next token or word.

BookCorpus is a dataset consisting of the text of around 7,000 self-published books scraped from the indie ebook distribution website Smashwords. It was the main corpus used to train the initial GPT model by OpenAI, and has been used as training data for other early large language models including Google's BERT. The dataset consists of around 985 million words, and the books that comprise it span a range of genres, including romance, science fiction, and fantasy.

<span class="mw-page-title-main">PaLM</span> Large language model developed by Google

PaLM is a 540 billion parameter transformer-based large language model developed by Google AI. Researchers also trained smaller versions of PaLM, 8 and 62 billion parameter models, to test the effects of model scale.

In machine learning, a neural scaling law is a scaling law relating parameters of a family of neural networks.

Claude is a family of large language models developed by Anthropic. The first model was released in March 2023. Claude 3, released in March 2024, can also analyze images.

References

  1. ↑ "gpt-2". GitHub. Archived from the original on 11 March 2023. Retrieved 13 March 2023.
  2. ↑ Vaswani, Ashish; Shazeer, Noam; Parmar, Niki; Uszkoreit, Jakob; Jones, Llion; Gomez, Aidan N; Kaiser, Łukasz; Polosukhin, Illia (2017). "Attention is All you Need" (PDF). Advances in Neural Information Processing Systems. 30. Curran Associates, Inc.
  3. 1 2 3 4 5 6 7 8 9 10 11 12 13 Radford, Alec; Narasimhan, Karthik; Salimans, Tim; Sutskever, Ilya (11 June 2018). "Improving Language Understanding by Generative Pre-Training" (PDF). OpenAI. p. 12. Archived (PDF) from the original on 26 January 2021. Retrieved 23 January 2021.
  4. 1 2 "GPT-1 to GPT-4: Each of OpenAI's GPT Models Explained and Compared". 11 April 2023. Archived from the original on 2023-04-15. Retrieved 2023-04-29.
  5. 1 2 Tsvetkov, Yulia (22 June 2017). "Opportunities and Challenges in Working with Low-Resource Languages" (PDF). Carnegie Mellon University. Archived (PDF) from the original on 31 March 2020. Retrieved 23 January 2021.
  6. ↑ Zhu, Yukun; Kiros, Ryan; Zemel, Richard; Salakhutdinov, Ruslan; Urtasun, Raquel; Torralba, Antonio; Fidler, Sanja (22 June 2015). "Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books". arXiv: 1506.06724 [cs.CV]. # of books: 11,038 / # of sentences: 74,004,228 / # of words: 984,846,357 / mean # of words per sentence: 13 / median # of words per sentence: 11
  7. ↑ Williams, Adina; Nangia, Nikita; Bowman, Samuel (1 June 2018). "A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference" (PDF). Association for Computational Linguistics. Archived (PDF) from the original on 11 February 2020. Retrieved 23 January 2021. At 433k examples, this resource is one of the largest corpora available for natural language inference (a.k.a. recognizing textual entailment), [...] offering data from ten distinct genres of written and spoken English [...] while supplying an explicit setting for evaluating cross-genre domain adaptation.
  8. ↑ Lai, Guokun; Xie, Qizhe; Hanxiao, Liu; Yang, Yiming; Hovy, Eduard (15 April 2017). "RACE: Large-scale ReAding Comprehension Dataset From Examinations". arXiv: 1704.04683 [cs.CL].
  9. ↑ Mostafazadeh, Nasrin; Roth, Michael; Louis, Annie; Chambers, Nathanael; Allen, James F. (3 April 2017). "LSDSem 2017 Shared Task: The Story Cloze Test" (PDF). Association for Computational Linguistics. Archived (PDF) from the original on 22 November 2020. Retrieved 23 January 2021. The LSDSem'17 shared task is the Story Cloze Test, a new evaluation for story understanding and script learning. This test provides a system with a four-sentence story and two possible endings, and the system must choose the correct ending. Successful narrative understanding (getting closer to human performance of 100%) requires systems to link various levels of semantics to commonsense knowledge.
  10. ↑ Wang, Alex; Singh, Amanpreet; Michael, Julian; Hill, Felix; Levy, Omar; Bowman, Samuel R. (20 April 2018). "GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding". arXiv: 1804.07461 [cs.CL].
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.