This repository contains code and resources for training, fine-tuning, and deploying large language models using Hugging Face's Transformers library. The aim of this repo is to provide a comprehensive guide and codebase for training large language models from scratch or fine-tuning pre-trained models for specific tasks.
If you're interested in a detailed, step-by-step explanation of how this project was built, including code walkthroughs and in-depth analysis, check out My Medium blog post- "Step-by-Step Guide to Train a Large Language Model (LLM) with code".
- Data preprocessing scripts to clean and tokenize text data.
- Model training scripts with customizable hyperparameters.
- Notebooks for interactive model exploration and experimentation.
- API for deploying trained models and generating text.
-
Clone this repository:
git clone https://github.com/SreeEswaran/Train-your-LLM.git cd Train-your-LLM -
Install dependencies:
pip install -r requirements.txt
-
Follow the instructions in each directory to preprocess data, train models, and deploy APIs.
Contributions are welcome! Feel free to submit bug reports, feature requests, or pull requests. For major changes, please open an issue first to discuss potential changes.
If you have any questions, suggestions, or just want to connect, feel free to reach out through the following platforms:
For Mentoring/Coaching/Guidance: https://topmate.io/SreeEswaran
LinkedIn: https://www.linkedin.com/in/sree-deekshitha-yerra
Medium Blogs: https://www.medium.com/@SreeEswaran