https://github.com/whisperpine/ollama-compose

Ollama docker compose.
https://github.com/whisperpine/ollama-compose

docker-compose large-model ollama

Last synced: about 2 months ago
JSON representation

Ollama docker compose.

• Host: GitHub
• URL: https://github.com/whisperpine/ollama-compose
• Owner: whisperpine
• License: mit
• Created: 2023-11-02T19:31:24.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2023-12-30T10:23:50.000Z (about 1 year ago)
• Last Synced: 2023-12-30T11:28:28.978Z (about 1 year ago)
• Topics: docker-compose, large-model, ollama
• Language: YAML
• Homepage:
• Size: 1.95 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# README

[Ollama](https://github.com/jmorganca/ollama)

docker compose.

## Prerequisites

### Hardware Requirements

Nvidia GPU.

### Memory Requirements

- 7b models generally require at least 8GB of RAM

- 13b models generally require at least 16GB of RAM

- 70b models generally require at least 64GB of RAM

## Getting Started

```sh

docker compose up -d

docker exec -it ollama bash

ollama run llama2

```

## References

- Ollama provides a [REST API](https://github.com/jmorganca/ollama/blob/main/docs/api.md) for running and managing models.

- Ollama supports a list of open-source models available on [ollama.ai/library](https://ollama.ai/library).