No description
Find a file
Daniel Hiltgen 58d95cc9bd Switch back to subprocessing for llama.cpp
This should resolve a number of memory leak and stability defects by allowing
us to isolate llama.cpp in a separate process and shutdown when idle, and
gracefully restart if it has problems.  This also serves as a first step to be
able to run multiple copies to support multiple models concurrently.
2024-04-01 16:48:18 -07:00
.github Switch back to subprocessing for llama.cpp 2024-04-01 16:48:18 -07:00
api change github.com/jmorganca/ollama to github.com/ollama/ollama (#3347) 2024-03-26 13:04:17 -07:00
app Switch back to subprocessing for llama.cpp 2024-04-01 16:48:18 -07:00
auth rerefactor 2024-02-15 05:56:45 +00:00
cmd Add gemma safetensors conversion (#3250) 2024-03-28 18:54:01 -07:00
convert Simplify model conversion (#3422) 2024-04-01 16:14:53 -07:00
docs remove need for $VSINSTALLDIR since build will fail if ninja cannot be found (#3350) 2024-03-26 16:23:16 -04:00
examples change github.com/jmorganca/ollama to github.com/ollama/ollama (#3347) 2024-03-26 13:04:17 -07:00
format update memory calcualtions 2024-04-01 13:16:32 -07:00
gpu Switch back to subprocessing for llama.cpp 2024-04-01 16:48:18 -07:00
integration change github.com/jmorganca/ollama to github.com/ollama/ollama (#3347) 2024-03-26 13:04:17 -07:00
llm Switch back to subprocessing for llama.cpp 2024-04-01 16:48:18 -07:00
macapp Move Mac App to a new dir 2024-02-15 05:56:45 +00:00
openai change github.com/jmorganca/ollama to github.com/ollama/ollama (#3347) 2024-03-26 13:04:17 -07:00
parser Save and load sessions (#2063) 2024-01-25 12:12:36 -08:00
progress change github.com/jmorganca/ollama to github.com/ollama/ollama (#3347) 2024-03-26 13:04:17 -07:00
readline Add gemma safetensors conversion (#3250) 2024-03-28 18:54:01 -07:00
scripts CI automation for tagging latest images 2024-03-28 16:07:37 -07:00
server Switch back to subprocessing for llama.cpp 2024-04-01 16:48:18 -07:00
version add version 2023-08-22 09:40:58 -07:00
.dockerignore add macapp to .dockerignore 2024-03-09 16:07:06 -08:00
.gitattributes rename .gitattributes 2024-03-23 12:40:31 +01:00
.gitignore Switch back to subprocessing for llama.cpp 2024-04-01 16:48:18 -07:00
.gitmodules Init submodule with new path 2024-01-04 13:00:13 -08:00
.golangci.yaml Add gemma safetensors conversion (#3250) 2024-03-28 18:54:01 -07:00
.prettierrc.json move .prettierrc.json to root 2023-07-02 17:34:46 -04:00
Dockerfile Switch back to subprocessing for llama.cpp 2024-04-01 16:48:18 -07:00
go.mod Add gemma safetensors conversion (#3250) 2024-03-28 18:54:01 -07:00
go.sum Convert Safetensors to an Ollama model (#2824) 2024-03-06 21:01:51 -08:00
LICENSE proto -> ollama 2023-06-26 15:57:13 -04:00
main.go change github.com/jmorganca/ollama to github.com/ollama/ollama (#3347) 2024-03-26 13:04:17 -07:00
README.md Add chromem-go to community integrations (#3437) 2024-04-01 11:17:37 -04:00

ollama

Ollama

Discord

Get up and running with large language models locally.

macOS

Download

Windows preview

Download

Linux

curl -fsSL https://ollama.com/install.sh | sh

Manual install instructions

Docker

The official Ollama Docker image ollama/ollama is available on Docker Hub.

Libraries

Quickstart

To run and chat with Llama 2:

ollama run llama2

Model library

Ollama supports a list of models available on ollama.com/library

Here are some example models that can be downloaded:

Model Parameters Size Download
Llama 2 7B 3.8GB ollama run llama2
Mistral 7B 4.1GB ollama run mistral
Dolphin Phi 2.7B 1.6GB ollama run dolphin-phi
Phi-2 2.7B 1.7GB ollama run phi
Neural Chat 7B 4.1GB ollama run neural-chat
Starling 7B 4.1GB ollama run starling-lm
Code Llama 7B 3.8GB ollama run codellama
Llama 2 Uncensored 7B 3.8GB ollama run llama2-uncensored
Llama 2 13B 13B 7.3GB ollama run llama2:13b
Llama 2 70B 70B 39GB ollama run llama2:70b
Orca Mini 3B 1.9GB ollama run orca-mini
Vicuna 7B 3.8GB ollama run vicuna
LLaVA 7B 4.5GB ollama run llava
Gemma 2B 1.4GB ollama run gemma:2b
Gemma 7B 4.8GB ollama run gemma:7b

Note: You should have at least 8 GB of RAM available to run the 7B models, 16 GB to run the 13B models, and 32 GB to run the 33B models.

Customize a model

Import from GGUF

Ollama supports importing GGUF models in the Modelfile:

  1. Create a file named Modelfile, with 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 example -f Modelfile
    
  3. Run the model

    ollama run example
    

Import from PyTorch or Safetensors

See the guide on importing models for more information.

Customize a prompt

Models from the Ollama library can be customized with a prompt. For example, to customize the llama2 model:

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 message
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.

CLI Reference

Create a model

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

ollama create mymodel -f ./Modelfile

Pull a model

ollama pull llama2

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

Remove a model

ollama rm llama2

Copy a model

ollama cp llama2 my-llama2

Multiline input

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.

Multimodal models

>>> What's in this image? /Users/jmorgan/Desktop/smile.png
The image features a yellow smiley face, which is likely the central focus of the picture.

Pass in prompt as arguments

$ 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.

List models on your computer

ollama list

Start Ollama

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

Building

Install cmake and go:

brew install cmake go

Then generate dependencies:

go generate ./...

Then build the binary:

go build .

More detailed instructions can be found in the developer guide

Running local builds

Next, start the server:

./ollama serve

Finally, in a separate shell, run a model:

./ollama run llama2

REST API

Ollama has a REST API for running and managing models.

Generate a response

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

Chat with a model

curl http://localhost:11434/api/chat -d '{
  "model": "mistral",
  "messages": [
    { "role": "user", "content": "why is the sky blue?" }
  ]
}'

See the API documentation for all endpoints.

Community Integrations

Web & Desktop

Terminal

Database

Package managers

Libraries

Mobile

Extensions & Plugins