AI offline × Termux : The Ollama Project

Protable AI in Your Device: The Ollama Project

the Ollama project! With Ollama

Getting Started

1. Prepare Your Device:

   • Ensure you have a device with ample RAM and storage space.
   • Install necessary packages:

     pkg i build-essential cmake golang git
     apt update
     pkg i gcc-8
             

     If needed, install GCC from the Pointless repository.

2. Clone the Repo:

   git clone https://github.com/ollama/ollama.git

3. Build and Install Dependencies:

   cd ollama
   go generate ./...
   go build .
       

4. Start the Server:

   ./ollama serve

Models Installing

• Pull the desired models from the repository:

  ./ollama pull gemma
  ./ollama pull openchat
      

Running Models

• Chat Session:

  ./ollama run gemma

• One Shot:

  ./ollama run gemma "Summarize for me: $(cat README.md)"

For More Details

• Check out the README.md for additional commands and API usage.
• Have fun bringing AI features everywhere you go with Ollama!

Pro Tip: Take a look at this conversation screenshot with llama2-uncensored for a glimpse of what's possible: Screenshot