The Machine Learning Engineer Courses

LLMs: Revisión de Qwen2 VL - Modelo de Lenguaje Visual de 2 Billones de Parámetros

Explora las capacidades del modelo Qwen2 VL de Alibaba Cloud, con 2 billones de parámetros, para análisis de video y respuesta a preguntas.

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

LLMOps: OpenVino Toolkit Quantization 4int LLama 3.2 3B and Inference on CPU

Optimize LLama3.2 3B model with OpenVino Toolkit: Convert to IR format, quantize to 4Int, and perform CPU inference using CoT prompts.

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

LLMOps: OpenVino Toolkit para Quantizar LLama 3.2 3B a 4int e Inferencia en CPU

Convierte y optimiza el modelo LLAMA3.2 3B con OpenVino Toolkit. Aprende a quantizar a 4Int y realizar inferencia en CPU utilizando CoT Prompts.

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

LLMOPS: Training a Small LLM (GPT-2) - Machine Learning and Data Science

Explore training a small LLM (GPT2) locally, understanding challenges and limitations of LLM development for individuals and small teams.

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

LLMOPS: Entrenamiento de un LLM nanoGPT (GPT2) en Español

Aprende a entrenar un LLM nanoGPT en español desde cero, crear datasets personalizados y realizar inferencias localmente utilizando un modelo GPT2 base.

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

MLOps MLflow: Logging and Inferencing with Fine-Tuned Vision Transformer Models

Master MLflow integration for Vision Transformer models, from fine-tuning registration to efficient inference deployment, enhancing your MLOps pipeline with practical implementation steps.

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

MLOps MLflow: Registering and Inferencing with Fine-Tuned Vision Transformer (ViT) - Spanish

Aprende a registrar y gestionar modelos Vision Transformer personalizados en MLflow, incluyendo el proceso de registro y recuperación para inferencia con ejemplos prácticos de código.

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

Building End-to-End RAG Applications with Unstructured Data - Part 3: Docker Integration

Dive into containerization with Docker and Docker Compose while building a RAG application that processes unstructured data using LangChain, multiple LLMs, and vector stores through Streamlit.

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

RAG: End-to-End Application - Hablando con Datos No Estructurados - Parte 3

Explore la implementación de RAG con Docker para crear una aplicación que procesa datos no estructurados usando Langchain, múltiples LLMs y diferentes vectorstores.

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

Building RAG Applications: Speaking with Unstructured Data Using LangChain - Part 2

Dive into building an end-to-end RAG application using Langchain, multiple LLMs, and vector stores to enable interactive conversations with unstructured data through a Streamlit interface.

• YouTube
• 1 hour 8 minutes
• Self-Paced
• Free Video

RAG: End-to-End Application - Speaking with Unstructured Data Part 2 - Spanish

Explore la implementación detallada de un sistema RAG multimodal usando Langchain, diversos LLMs y vectorstores para procesar datos no estructurados, con enfoque práctico en código y arquitectura.

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

Building RAG Applications: Speaking with Unstructured Data Using LangChain - Part 1

Dive into building a RAG application using Langchain, multiple LLMs, and vector stores to enable interactive conversations with unstructured data through a Streamlit interface.

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

RAG: End-to-End Application - Speaking with Unstructured Data - Part 1 (Spanish)

Descubre cómo construir una aplicación RAG completa para interactuar con datos no estructurados usando Langchain, múltiples LLMs, y diferentes vectorstores. Implementación práctica con Streamlit y Docker.

• YouTube
• 1 hour
• Self-Paced
• Free Video

Building RAG Applications with PDFs Using LlamaIndex - Comparing Gemini Pro and Nvidia NIM Llama 3.2

Master RAG implementation using LlamaIndex to create PDF-based conversational agents with Gemini Pro and Nvidia NIM Llama 3.2, leveraging PymuPDF for text and image extraction.

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

RAG - Extracting Information from PDFs Using LlamaIndex, Gemini, and Nvidia NIM with Llama 3.2

Aprende a extraer información de PDFs utilizando LlamaIndex, implementando modelos como Gemini y Nvidia NIM para embeddings junto con LLama 3.2 para procesamiento de lenguaje natural.

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