Language model: Difference between revisions

Revision as of 16:51, 10 July 2024

Revision as of 12:33, 16 July 2024

Line 7:

[[Large language model]]s, currently their most advanced form, are a combination of larger datasets (frequently using words [[Web scraping|scraped]] from the public internet), [[feedforward neural network]]s, and [[transformer (machine learning)|transformer]]s. They have superseded [[recurrent neural network]]-based models, which had previously superseded the pure statistical models, such as [[Word n-gram language model|word ''n''-gram language model]].

Small language models are scaled down LLMs that are trained on smaller, private, or proprietary data sets. Also referred to as "personal language models" since they are typically trained on personal, not public data.<ref>{{Cite web |title=Differences Between Personal Language Models and Large Language Models |url=https://www.personal.ai/plm-personal-and-large-language-models |access-date=2024-07-10 |website=www.personal.ai |language=en}}</ref>

== Pure statistical models ==