Venelin Valkov Courses

Object Detection on Custom Dataset with YOLO - Fine-Tuning with PyTorch and Python Tutorial

7 ratings

Fine-tune YOLOv5 on a custom clothing dataset, evaluate its object-detection performance, and run inference on new images.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

DeepSeek Coder- AI Writes Code - LLM For Code Generation Beats ChatGPT, ChatDev & Code Llama

2 ratings

Explore DeepSeek Coder's capabilities in coding tasks, from simple functions to complex problems and app development. Compare its performance to other AI models in various programming scenarios.

• YouTube
• 24 minutes
• Self-Paced
• Free Video

What is RAG? The Complete Tutorial - From Scratch to Deployed API on Production - LangChain and Ollama

1 rating

Master Retrieval-Augmented Generation by building a complete system from scratch using Python, LangChain, and Ollama, then deploy it as a production-ready API with Docker.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Build 100% Local AI Agent to Chat with Your Files - Private AI Knowledge Base with MCP and RAG

1 rating

Discover how to build CogVault, a completely local AI agent that chats with your PDFs and documents using Qwen3, MCP tools, RAG, and Streamlit without cloud dependency.

• YouTube
• 43 minutes
• Self-Paced
• Free Video

Build Powerful AI Agents with ChatGPT-GPT-4 - Python Tutorial for Cryptocurrency Analysis

1 rating

Explore AutoGen for creating AI agents with LLMs. Learn to build a stock price analyzer and a multi-agent system for cryptocurrency analysis using Python and GPT models.

• YouTube
• 22 minutes
• Self-Paced
• Free Video

Vectorless RAG - Local Financial RAG Without Vector Database - Tree-Based Indexing with Ollama

1 rating

Discover how to build a local RAG system without vector databases using tree-based indexing, Ollama, and LangChain for financial document analysis.

• YouTube
• 18 minutes
• Self-Paced
• Free Video

Evaluate LayoutLMv3 for Document Classification - Save & Load Model to HuggingFace Hub

1 rating

Evaluate a LayoutLMv3 document classifier, publish it to Hugging Face Hub, run single-image inference, and analyze errors with a confusion matrix.

• YouTube
• 27 minutes
• Self-Paced
• Free Video

Local Llama 3.2 (3B) Tutorial - Summarization, Structured Text Extraction, and Data Labelling

1 rating

Explore Llama 3.2 (3B) on Ollama for summarization, data extraction, and labeling. Learn setup, coding, and practical applications in this hands-on tutorial.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Building a Private Chatbot with LangChain, Ollama and Qwen 2.5 for Mobile App Review Analysis

Learn to build a private chatbot for analyzing mobile app reviews using LangChain, Ollama, and Qwen 2.5, with step-by-step guidance on local LLM implementation and data analysis.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Testing Microsoft Phi-4 Model for Text Processing and Data Analysis

Explore Microsoft's Phi-4 language model through hands-on testing of summarization, data labeling, and text extraction capabilities using Ollama, with practical demonstrations and performance comparisons.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Fine-tuning Llama 3.2 for Mental Health Sentiment Analysis Using TorchTune

Master fine-tuning techniques for Llama 3.2 using torchtune, focusing on sentiment analysis for mental health data with practical implementation steps on a single GPU.

• YouTube
• 22 minutes
• Self-Paced
• Free Video

Build Better RAGs with Contextual Retrieval

Enhance RAG systems with contextual retrieval to improve context chunk quality and generate more accurate answers. Learn implementation techniques and practical applications.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

Build 100% Local Chatbot with Gemma 3, Ollama and LangChain - AI Assistant with Memory and Tool Use

Learn to build a local AI wellness coach with Gemma 3, Ollama, and LangChain that remembers user information, features persistent memory, and includes tool integration—all without cloud dependencies.

• YouTube
• 37 minutes
• Self-Paced
• Free Video

Gemma 3 Local Test: Coding, Data Extraction, Data Labelling, Summarization, RAG

Explore Gemma 3's capabilities through practical tests with Ollama, including coding, data extraction, summarization, and RAG implementations in a local environment.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

Fine-Tuning Qwen3 on Your Data Using Single GPU - Sentiment Analysis for Cryptocurrency Tweets

Learn how to fine-tune Qwen3 (0.6B) on custom data for sentiment analysis of cryptocurrency tweets, from data preparation to model evaluation, using LoRA for efficient training on a single GPU.

• YouTube
• 47 minutes
• Self-Paced
• Free Video