# Model Index Large language models (LLMs) are advanced AI algorithms trained on vast datasets of text. They can understand, generate, and interpret human language with remarkable accuracy. These models are capable of performing a wide range of language-based tasks, from answering questions and summarizing texts to creating original content. In the context of Matrix One, LLMs power the conversational abilities of AI agents, enabling them to engage in realistic and nuanced interactions with users. LoRA (Low-Rank Adaptation of LLMs) is a technique used to fine-tune large AI models, like LLMs, in a more efficient and resource-light manner. It adapts a pre-trained model to specific tasks or datasets by only modifying a small portion of the model's parameters, preserving the original structure and knowledge. This approach allows for personalized or specialized enhancements without the need for extensive retraining. The Model Index is a key component of the protocol, providing an extensive catalogue with 1000s of open-source and licensed models available for developers to include in their apps with a single click. Developers can enable their end-users to choose the model that powers their agent likewise for character creators. Furthermore as well as and provide them access to the training data sets generated through interaction with their models. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.matrix.one/protocol/infrastructure/model-index.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.