Venelin Valkov Courses

Deploy LLM to Production on Single GPU - REST API for Falcon 7B with QLoRA on Inference Endpoints

Learn to deploy a fine-tuned Falcon 7B model with QLoRA to production using HuggingFace Inference Endpoints, creating a REST API for efficient and scalable inference on a single GPU.

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

Analyzing Cryptocurrency Sentiment on Twitter with LangChain and ChatGPT

Learn to analyze cryptocurrency sentiment on Twitter using LangChain and ChatGPT. Create custom prompts, integrate with LLMChain, and build a Streamlit app for real-time sentiment analysis.

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

Fine-Tuning Alpaca- Train Alpaca LoRa for Sentiment Analysis on a Custom Dataset

Learn to fine-tune Llama 7B with Alpaca LoRa on a custom bitcoin sentiment dataset. Covers data preprocessing, model training, and performance analysis for sentiment detection in cryptocurrency tweets.

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

Loaders, Indexes & Vectorstores in LangChain - Question Answering on PDF Files with ChatGPT

Learn to use LangChain for advanced document processing, including loading PDFs, creating embeddings, and performing question-answering with ChatGPT. Explore data loaders, indexes, and vector stores for efficient text analysis.

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

Build ChatGPT Chatbots with LangChain Memory - Understanding and Implementing Memory in Conversations

Explore different memory types for ChatGPT chatbots using LangChain, including buffer, summary, window, and vectorstore memory. Learn implementation techniques for coherent conversations.

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

Customer Support Chatbot Using Custom Knowledge Base with LangChain and Private LLM

Build a customer support chatbot using custom knowledge, LangChain, and a private LLM. Learn to create, embed data, and implement conversational and QA chains for real-time responses on a single GPU.

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

Exploring the ChatGPT API with Python - Multiple Completions, Max Tokens, Temperature

Learn to use ChatGPT API with Python: create requests, manage conversations, explore multiple completions, adjust temperature, and count tokens using tiktoken. Perfect for beginners and those looking to expand their skills.

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

Key Principles for Optimizing LLaMA 2 and ChatGPT Responses - Mastering AI Prompt Engineering

Discover 26 key principles for optimizing LLaMA 2 and ChatGPT responses, covering prompt structuring, task breakdown, and performance improvement techniques for AI projects.

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

SDXL Turbo - Instant High-Quality Text-to-Image Generation with One-Step AI Model

Explore SDXL Turbo, a fast text-to-image AI model. Learn setup, key parameters, and generate high-quality images across various themes. Discover its versatility and speed in creating stunning visuals.

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

Google Gemini - Technical Report on Model Architecture, Dataset, and Training

Explore Google's Gemini AI model family: architecture, datasets, and performance across text, image, video, and speech benchmarks. Learn how it advances multimodal AI and sets new records.

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

MemGPT - Unlimited Context Window for LLMs: Paper Review, Installation, and Demo

Explore MemGPT's innovative approach to overcoming LLM token limits using hierarchical memory. Learn installation, usage, and how to enhance AI interactions with personas and user data.

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

Zephyr 7B Beta - Comparing a 7B LLM with 70B Models

Explore Zephyr 7B Beta's performance against larger models through paper review and hands-on Google Colab tutorial. Learn setup, prompting, and practical applications in math, coding, and data tasks.

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

Chat with Multiple PDFs Using Llama 2 and LangChain - Use Private LLM and Free Embeddings for QA

Learn to build a chatbot using Llama 2 and LangChain to answer questions from multiple PDFs. Explore private LLM integration, vector stores, and efficient document retrieval techniques.

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

Generative Agents- Simulating Human Behavior with ChatGPT

Explore the breakthrough of Generative Agents, simulating human-like behavior in interactive environments using Large Language Models, with key components and real-world applications.

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

LangChain Models- ChatGPT, Flan Alpaca, OpenAI Embeddings, Prompt Templates & Streaming

Explore LangChain's capabilities with chat models, embeddings, and prompt templates. Learn to enhance responses and stream output for efficient language model integration.

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