> ## Documentation Index
> Fetch the complete documentation index at: https://anaconda.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# LLM

Install the `llm` package in your environment:

```sh theme={null}
conda install conda-forge::llm
```

To list the Anaconda AI models, run:

```sh theme={null}
llm models list -q anaconda
```

When you invoke a model, `llm` first ensures that the model has been downloaded, then starts the server using Anaconda AI. Standard OpenAI parameters and server configuration options are supported. For example:

```sh theme={null}
llm -m 'anaconda:meta-llama/llama-2-7b-chat-hf_Q4_K_M.gguf' -o temperature 0.1 'what is pi?'
```

To use an already running server, use `server/<server-name>` as the model identifier:

```bash theme={null}
llm -m 'anaconda:server/my-server' -o temperature 0.1 'what is pi?'
```

To view server parameters, run:

```sh theme={null}
llm models list -q anaconda --options
```

For more information on using the `llm` package, see the [official documentation](https://llm.datasette.io/en/stable/index.html).