Julien Heiduk
Let's talk about recommandation systems and ML in real-world business scenarios.
Fine-Tune LLMs with QLoRA
Fine-tune a large language model with QLoRA on a single GPU, then serve it at high throughput using vLLM’s PagedAttention engine.
Fine-Tune LLMs with QLoRAGCN with PyTorch for Co-Purchase Recommendation
Graph Convolutional Networks turn co-purchase data into a graph and learn item embeddings for recommendation. A full PyTorch Geometric implementation included.
GCN with PyTorch for Co-Purchase RecommendationRetrieval-Augmented Generation with LangChain
RAG grounds LLM answers in your own documents. Learn how to build a production-ready RAG pipeline with LangChain, FAISS, and OpenAI in Python.
Retrieval-Augmented Generation with LangChainModel Context Protocol server with FastMCP
This tutorial explores how to create a MCP server with FastMCP and why use it.
Model Context Protocol server with FastMCPCleora part 2: How to create user embeddings?
This tutorial explores how to generate user embeddings from interaction data using Cleora, a high-performance graph embedding tool — ideal for recommendation systems and graph-based machine learning.
Cleora part 2: How to create user embeddings?