YouTipOllama
Run large language models locally on your machine.
# Install and run
ollama pull llama2
ollama run llama2
# API
curl http://localhost:11434/api/generate -d '{
"model": "llama2",
"prompt": "Hello!"
}'Summary
- Ollama runs LLMs locally
- Supports Llama2, Mistral, CodeLlama, and more