Fine-tuning TinyLlama with custom Medical dataset for Beginners | HuggingFace | TinyLlama
In this hands-on tutorial, we'll dive into fine-tuning TinyLlama for medical text dialogue conversational AI application What you'll learn Setting up TinyLlama for medical domain adaptation Implementing fine-tuning with minimal computing resources Understanding Weights & Biases integration for training monitoring Working with practical batch sizes and gradient accumulation - Real-world considerations and optimization strategies ⭐️ Timeline ⭐️ 00:00 : Step-by-step code walkthrough - Llama 8B model - HF TinyLLama 03:46 : HF TinyLlama and Lora adaptation for Resource-conscious training approach 12:20 : Data preparation and Finetuning 21:12 : Parameter optimization for optimal performance 23:21 : Save the model, push to HuggingFace and test the finetuned-model 26:51 : Conclusion 📌 Notebook: https://www.kaggle.com/code/aboniasoj... 📌 Or find the notebook here: https://github.com/Abonia1/LLM-Finetu... 📌 Dataset: https://huggingface.co/datasets/rusla... 📌 Fine-tuned model in HF: Abonia/tinyllama-medical-chat Note: This tutorial focuses on educational concepts using minimal resources. Production deployment would require additional optimization. Planned for Llama 8B fientunig as because my request to use this model is still in progress so Meantime we will fine tune TinyLlama chat model. ___________________________________________________________________________ 🔔 Get our Newsletter and Featured Articles: https://abonia1.github.io/newsletter/ 🔗 Linkedin: / aboniasojasingarayar 🔗 Find me on Github: https://github.com/Abonia1 🔗 Medium Articles: / abonia #LLM # finetuning #MachineLearning #AI #TinyLlama #MedicalAI #Tutorial #Python #LLM

Fine tune Gemma 3, Qwen3, Llama 4, Phi 4 and Mistral Small with Unsloth and Transformers

What is RAG (Retrieval-Augmented Generation)?

EASIEST Way to Fine-Tune a LLM and Use It With Ollama

Fine Tune DeepSeek R1 | Build a Medical Chatbot

Searching Data in Documents Using Tesseract OCR & Regex - Part 5

Transformers, the tech behind LLMs | Deep Learning Chapter 5

RAG Crash Course for Beginners

EASIEST Way to Train LLM Train w/ unsloth (2x faster with 70% less GPU memory required)

Learn Pandas in 30 Minutes - Python Pandas Tutorial

Finetuning Llama2 7B on Personal Dataset with an IITian | ML/LLM Project

Finetune LLMs to teach them ANYTHING with Huggingface and Pytorch | Step-by-step tutorial

Fetching data from an API

Turing Award Winner: Disagreeing with Google, Postgres, Future Problems | Mike Stonebraker

MCP Server in Python | Anthropic's Model Context Protocol (MCP) vs. Google's Agent2Agent (A2A)|Agent

Final Project Demo
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLDbV4izF3i-wxevCVIn7FJjoy1vlA)
Yann LeCun's $1B Bet Against LLMs [Part 1]

Fine-tuning Tiny LLM on Your Data | Sentiment Analysis with TinyLlama and LoRA on a Single GPU

But what is a neural network? | Deep learning chapter 1

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

