2 Pretrained Models
The more complex the mind, the greater the need for the simplicity of play.—Isaac Asimov, in “I, Robot”
Pretrained models are AI systems that are capable of processing large amounts of data and working on a dedicated task. Pretrained models are not a Swiss army knife with a lot of different features, but typically, they work well for one specific task. Then came large language models (LLMs). At that time, there were individual models for each task. In the field of natural language processing (NLP), a task might be text classification, question answering, zero-shot classification, translation, summarization, feature extraction, text generation, fill-mask, or sentence similarity. The list is not exhaustive, and more tasks will ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access