# Language model | | 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. | | ---- | ---- | | | wikipedia:: [Language model](https://en.wikipedia.org/wiki/Language_model) | | | | [[Large Language Model]] - Proprietary - Open Source - Benefits - Transparent/open - [[Open Source]] - Big one - you can fine-tune any open model however you want - Community contributions, etc - Can benchmark them according to how truthful they are - LLAMA2 - many/most open source models are based on this one - [[Meta Platforms Inc]] - VICUNA - BLOOM - Running locally - [[LM Studio]] - [[Hugging Face]] - Training