Enhancing an Existing LLM Model with Domain-specific Jenkins knowledge

Project goal: To develop an app using an existing open-source LLM model with data collected for domain-specific Jenkins knowledge one can fine-tune locally and set up with a proper UI for the user to interact with

Skills to study/improve: Python, LLM, AI/ML, Jenkins, UI

NOTE: This idea is published as a draft under active discussion, but it is confirmed in principle. It is FINE to apply to it. The scope and the suggested implementation may change significantly before the final version is published. Sections like quickstart guide and newbie-friendly issues may be also missing. As a contributor, you are welcome to request additional information and to join the discussions using channels linked on this page.

Details

Background

This full-stack project focuses on a proof-of-concept (PoC) to fine-tune an existing open-source LLM model Llama 2 with domain-specific Jenkins data to be compiled, wrangled, and processed by the contributor as a part of an application to be developed, with a minimalistic UI to interact with the user. The contributor will get to be involved in every step of the application development process, from data collection, wrangling, and processing to fine-tuning the model and developing the UI.

Potential Mentors

Project Links

Organization Links

> Go back to other GSoC 2024 project ideas

On this page

Connect