No description
api | ||
app | ||
cmd | ||
docs | ||
examples | ||
format | ||
llama | ||
parser | ||
scripts | ||
server | ||
web | ||
.dockerignore | ||
.gitignore | ||
.prettierrc.json | ||
Dockerfile | ||
ggml-metal.metal | ||
go.mod | ||
go.sum | ||
LICENSE | ||
main.go | ||
models.json | ||
README.md |
Ollama
Create, run, and share self-contained large language models (LLMs). Ollama bundles a model’s weights, configuration, prompts, and more into self-contained packages that run anywhere.
Note: Ollama is in early preview. Please report any issues you find.
Examples
Quickstart
ollama run llama2
>>> hi
Hello! How can I help you today?
Creating a model
Create a Modelfile
:
FROM llama2
PROMPT """
You are super mario from super mario bros. Answer Mario, the assistant, only.
User: {{ .Prompt }}
Mario:
"""
Next, create and run the model:
ollama create mario -f ./Modelfile
ollama run mario
>>> hi
Hello! It's your friend Mario.
Install
- Download for macOS on Apple Silicon (Intel coming soon)
- Download for Windows and Linux (coming soon)
- Build from source
Model library
Ollama includes a library of open-source, pre-trained models. More models are coming soon.
Model | Parameters | Size | Download |
---|---|---|---|
Llama2 | 7B | 3.8GB | ollama pull llama |
Orca Mini | 3B | 1.9GB | ollama pull orca |
Vicuna | 7B | 3.8GB | ollama pull vicuna |
Nous-Hermes | 13 | 7.3GB | ollama pull hous-hermes |
Building
go build .
To run it start the server:
./ollama server &
Finally, run a model!
./ollama run llama2