https://github.com/tankibaj/ollama-demo

Experimenting with self-hosted LLM models using Ollama
https://github.com/tankibaj/ollama-demo

Last synced: 5 months ago
JSON representation

Experimenting with self-hosted LLM models using Ollama

• Host: GitHub
• URL: https://github.com/tankibaj/ollama-demo
• Owner: tankibaj
• Created: 2024-02-15T20:18:47.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-02-16T00:10:51.000Z (over 1 year ago)
• Last Synced: 2025-02-17T21:36:55.799Z (8 months ago)
• Language: Python
• Homepage:
• Size: 1.58 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
## Quick Ollama installation

- Spin up Ollama container

    ```bash

    docker compose up -d

    ```

- Run Llama2 model inside the container

    ```bash

    docker exec -it ollama ollama run llama2

    ```

- Run llava (Vision Assistant) model inside the container

    ```bash

    docker exec -it ollama ollama run llava

    ```

- Run odellama model inside the container

    ```bash

    docker exec -it ollama ollama run codellama

    ```

## Test LLM models

- Install required packages

    ```bash

    pip install -r requirements.txt

    ```

- llama2

    ```bash

    py llama2.py

    ```

- codellama

    ```bash

    py codellama.py

    ```

- llava (Vision Assistant)

    ```bash

    py vision.py

    ```