Tuesday, July 9, 2024

How to run LLM in local machine

 Here we will discuss the steps to install LLM in local machine on Windows:

Steps:

  • Goto https://ollama.com/download/windows
  • Download & install the Ollama platform on your machine by clicking the OllamaSetup.exe file
  • Once the installation is completed, to check the Ollama platform is running navigate to http://localhost:11434/ & check the status. 
  • If the platform is installed successfully it will show :Ollama is running
  • Now we need to install the language model.
  • Navigate to https://ollama.com/library
  • You can now install any language model based on your need
  • To run the language model, goto powershell prompt
  • Run the command ollama run <language_model_name> e.g. ollama run llama2
  • Once the LLM is installed, it will provide a command prompt to interact like Chatgpt
  • The API of Ollama can be used to interact using Spring AI


Further readings:

https://thenewstack.io/how-to-set-up-and-run-a-local-llm-with-ollama-and-llama-2/

https://www.kdnuggets.com/ollama-tutorial-running-llms-locally-made-super-simple

https://www.youtube.com/watch?v=5ecArhs6d7I&pp=ygULamF2YSB0ZWNoaWU%3D


Sample Codebase:

https://github.com/Java-Techie-jt/spring-ai-llama2/tree/main

No comments:

Encryption using Google Tink

Google Tink is a tool which provides an End to End solution for Encryption/Decryption. Steps: Step #1: Create the Encryption key. Goto https...