Raspberry PI LLM Resources

Deepseek, Phi3, TinyLlama and Llama3 models on our Raspberry Pi. The first two of these are meant to be lightweight models, the last one however is not.Now, we will be testing the Deepseek, Phi3, TinyLlama and Llama3 models on our Raspberry Pi. The first two of these are meant to be lightweight models, the last one however is not.

• ollama is a virtual pet created by DeepSeek. It can be trained in various AI tasks, including programming, mathematics, creative arts, and more, using a chat interface where users can ask questions or receive responses.

• tinyllama, on the other hand, is a Python library for generating code from prompts. It's often used to create small-scale AI models that can respond to specific queries by
  writing short pieces of code (e.g., for creating websites, games, or social media posts)

Sample usage with tinyllama

curl http://localhost:11434/api/generate -d '{
  "model": "tinyllama",
  "prompt": "Why is the capital of Australia?",
  "stream": false