In this video, we dive deep into the world of Large Language Models (LLMs) by learning how to fine-tune one from scratch on a text summarization task! We will be using the TinyStories 19 Million parameter base model and fine-tuning it on the TinyStories instruct dataset for summarizing stories.
We will walk through the initial base model and how it generates tiny stories. We will further train that model on summarization tasks. The lecture involves dataset preparation and fine-tuning from scratch with the Pytorch framework. We will also understand how to shift the model parameters and training dataset on GPU for speeding up the training process.
Access the Notebook: https://github.com/SauravP97/llm-fine...
Github Repo: https://github.com/SauravP97/llm-fine...
Fine-tuned TinyStories 19M model: https://huggingface.co/SauravP97/tiny...
TinyStories Paper: https://arxiv.org/pdf/2305.07759
My Socials 🚀
🙋♂️ Linkedin: / saurav-prateek-7b2096140
🧑💻 Github: https://github.com/SauravP97
☀️ Instagram: / saurav_prateek
⚡️ Book a 1:1 session with me for Interview Preparation and Career guidance, Mock Interviews and Resume Review on Topmate: https://topmate.io/saurav_prateek
Sur cette page du site, vous pouvez voir la vidéo en ligne Fine-Tune LLM on Text Summarization task from scratch | Pytorch | Python durée heure minute seconde en bonne qualité , qui a été Téléchargé par l'utilisateur Saurav Prateek 10 avril 2026, Partagez le lien avec vos amis et connaissances, sur youtube cette vidéo a déjà été regardée 532 fois et il a aimé 28 téléspectateurs. Bon visionnage!