Get up and running with large language models locally.

Download

curl https://ollama.ai/install.sh | sh

Manual install instructions

coming soon

To run and chat with Llama 2:

ollama run llama2

Ollama supports a list of open-source models available on ollama.ai/library

Here are some example open-source models that can be downloaded:

Note: You should have at least 8 GB of RAM to run the 3B models, 16 GB to run the 7B models, and 32 GB to run the 13B models.

Ollama supports importing GGUF and GGML file formats in the Modelfile. This means if you have a model that is not in the Ollama library, you can create it, iterate on it, and upload it to the Ollama library to share with others when you are ready.

1. Create a file named Modelfile, and add a FROM instruction with the local filepath to the model you want to import.

   FROM ./vicuna-33b.Q4_0.gguf
   

2. Create the model in Ollama

   ollama create name -f path_to_modelfile
   

3. Run the model

   ollama run name
   

Models from the Ollama library can be customized with a prompt. The example

ollama pull llama2

Create a Modelfile:

FROM llama2

# set the temperature to 1 [higher is more creative, lower is more coherent]
PARAMETER temperature 1

# set the system prompt
SYSTEM """
You are Mario from Super Mario Bros. Answer as Mario, the assistant, only.
"""

Next, create and run the model:

ollama create mario -f ./Modelfile
ollama run mario
>>> hi
Hello! It's your friend Mario.

For more examples, see the examples directory. For more information on working with a Modelfile, see the Modelfile documentation.

ollama create is used to create a model from a Modelfile.

ollama pull llama2

This command can also be used to update a local model. Only the diff will be pulled.

ollama rm llama2

ollama cp llama2 my-llama2

For multiline input, you can wrap text with """:

>>> """Hello,
... world!
... """
I'm a basic program that prints the famous "Hello, world!" message to the console.

$ ollama run llama2 "summarize this file:" "$(cat README.md)"
 Ollama is a lightweight, extensible framework for building and running language models on the local machine. It provides a simple API for creating, running, and managing models, as well as a library of pre-built models that can be easily used in a variety of applications.

ollama list

ollama serve is used when you want to start ollama without running the desktop application.

Install cmake and go:

brew install cmake
brew install go

Then generate dependencies and build:

go generate ./...
go build .

Next, start the server:

./ollama serve

Finally, in a separate shell, run a model:

./ollama run llama2

See the API documentation for all endpoints.

Ollama has an API for running and managing models. For example to generate text from a model:

curl -X POST https://localhost:11434/api/generate -d '{
  "model": "llama2",
  "prompt":"Why is the sky blue?"
}'

• LangChain and LangChain.js with example
• LlamaIndex
• Raycast extension
• Discollama (Discord bot inside the Ollama discord channel)
• Continue
• Obsidian Ollama plugin
• Dagger Chatbot
• LiteLLM
• Discord AI Bot
• HTML UI
• Typescript UI
• Dumbar
• Emacs client