Yuvraj Singh

Yuvraj Singh

NLP | Interested in RL Reasoning in LLMs and Multimodal LLMs | Exploring the intersection of Research and Engineering

Fine Tuning using PEFT

Fine Tuning using PEFT

Category: Fine-tuning
Framework: PyTorch
Dataset: Custom
Created: March 01, 2025
GitHub: View Implementation

Overview

From scratch implementation of Fine Tuning using PEFT

Technical Details

  • Framework: PyTorch
  • Dataset: Custom
  • Category: Fine-tuning

Implementation Details

I implemented a simple fine tuning script using peft (qlora and bnb) for fine tuning llms. Also added a file for training encoder type models.

Frameworks:

Pytorch

Source Code

📁 GitHub Repository: Fine Tuning using PEFT

View the complete implementation, training scripts, and documentation on GitHub.