LLM Reference
Concepts & capability filters

Pretrained Model

A pretrained model is the base model produced by self-supervised training on large text corpora, before instruction or chat tuning.

Category
Not classified
Difficulty
Not classified
Aliases
None tracked
Last reviewed
2026-07-02

Key facts

  • Base checkpoints predict text but do not reliably follow instructions, so for most build decisions you deploy the instruct or chat variant; you reach for the raw base model mainly when you are doing your own fine-tuning.

Models Mentioning Pretrained Model(1)