UBIAI Tutorials
Step-by-Step Guides to Master LLM Fine-Tuning & AI Workflows
Expert guidance
In-depth knowledge
Real Use-Cases
Practical, easy-to-follow tutorials to fine-tune LLMs and optimize AI models.
Whether you’re a beginner or an expert, find tutorials tailored to your level.
the latest tools and techniques
Learn how to train, deploy, and integrate AI models for finance, healthcare, and more.
Our AI Tutorials
Take control of your future and join the AI revolution today!
Fine-Tune Qwen 2.5 Vision Language Model for Document Information Extraction
Mar 14, 2025
This tutorial breaks down the process of fine-tuning Qwen 2.5, a powerful vision-language model for extracting structured data from documents.
What You’ll Learn:
- How Vision Language Models Work
- Key Differences Between Text & Vision Models
- Step-by-Step Fine-Tuning Process
- Practical Tips for Better Results
Fine Tune & Deploy Custom AI Models in Minutes
Mar 14, 2025
In this step-by-step tutorial, you’ll learn how to build, fine-tune, and deploy custom AI models effortlessly—no extensive coding required!
What You’ll Learn:
- Setting up and managing your datasets
- Fine-tuning AI models for various applications
- Evaluating performance with built-in metrics
- Deploying models with API integration
Fine-tuning Qwen for Reliable Information Extraction From Documents
Mar 4, 2025
Information extraction is a major challenge for businesses handling invoices, contracts, and reports. With LLMs fine-tuned on your data, you can automate document processing more accurately and efficiently.
In this tutorial, we’ll walk you through:
- How Qwen stacks up against top AI models
- Using LlamaParse to extract structured text from documents
- Zero-shot performance testing for extracting key details
- Fine-tuning Qwen to improve accuracy and reduce hallucinations
- A step-by-step, hands-on demo with real-world applications
Fine-Tuning LLMs : Build a Reasoning Agent
Simple tutorial for smarter AI
Feb 10, 2025
Want to take Large Language Models (LLMs) to the next level? In this tutorial, we’ll show you how to fine-tune smaller models for math and coding tasks and integrate them into an AI reasoning agent that outperforms vanilla LLMs!
What You’ll Learn:
- Why vanilla LLMs struggle with reasoning-intensive tasks
- How to fine-tune smaller models on math & coding datasets
- How to build an AI agent that applies logical reasoning
- Step-by-step implementation using function calling & tool integration
How to Fine-Tune LLMs on Your Own Dataset
A No-Code Tutorial
Feb 3, 2025
Want to fine-tune a Large Language Model (LLM) on your own dataset—without complex coding?
In this step-by-step tutorial, we show you how to use UbiAI to fine-tune an LLM using your own data, making AI customization more accessible than ever!
What You’ll Learn:
- Uploading & structuring your dataset
- Configuring and training your LLM with ease
- Testing, optimizing, and integrating your fine-tuned model
Synthetic Data Generation for SQL Commands
A Step-by-Step Tutorial
Jan 6, 2025
Struggling to find high-quality data for fine-tuning your AI models? Learn how to generate synthetic data to overcome data scarcity in this in-depth tutorial!
This tutorial walks you through:
- Why synthetic data is crucial in today’s AI landscape.
- How to create an SQL commands dataset tailored to your use case.
- Tips on refining, filtering, and evaluating your generated data using reward models.
🔗 Example notebook
How to fine-tune your own AI model
From creating datasets to deploying a trained model
Dec 30, 2024
In this tutorial, we take you through the entire process of fine-tuning a language model, from creating datasets to deploying your trained model. Whether you’re working on text generation, named entity recognition, or document classification, this guide will help you get started quickly and effectively.
What you’ll learn:
- Preparing datasets (CSV uploads, mapping, and validation).
- Training models for tasks like text generation and classification.
- Using real-time metrics (F1 score, precision, recall) to evaluate performance.
- Testing models in the playground and integrating via API.
Fine-Tuning LLaMA-3 for Psychology Question Answering
Using LoRA and Unsloth
Dec 17, 2024
In this tutorial, we walk you through the process of finetuning the Llama3 language model to answer psychology-related questions. Whether you’re new to AI or looking to dive deeper into the world of language model customization, this video provides step-by-step instructions to help you tailor Llama3 for specialized tasks in psychology.
You’ll learn how to:
- Set up the Llama3 model for training
- Prepare and preprocess psychology datasets
- Fine-tune the model with effective strategies
- Test and evaluate its performance
What are you waiting for?
Automate your process!
