LLMs, agents, RAG and ML
This guide shows you how to adapt Llama 3.2 3B for specific tasks using LoRA on a single NVIDIA GPU with PyTorch. Follow…
Build a retrieval-augmented generation system using Python, LangChain, and Weaviate vector database. Install dependencie…
Initialize a Weaviate instance, configure a text2vec-huggingface embedding model, and create a collection with a vector…
Reduce memory usage and speed up Llama 3 inference on Raspberry Pi by quantizing the model weights to 4-bit or 8-bit usi…
Install Qdrant locally or on a server to build a Retrieval-Augmented Generation pipeline. This guide covers Docker setup…
Configure a single GPU environment to train a LoRA adapter for Stable Diffusion XL using PyTorch and Diffusers. Follow t…
Install CUDA, cuDNN, PyTorch, and Diffusers to prepare a Linux system for training Stable Diffusion models with a NVIDIA…
Build a working text classifier in under 30 lines of Python code using TF-IDF vectorization and a Logistic Regression mo…
Get PyTorch 2.3.0 installed on Ubuntu 24.04 with CUDA 12.1 support. Follow these steps to configure the environment and…
Install transformers and datasets libraries, load the base model, prepare a CSV dataset, run the training script, and ev…
Build a retrieval-augmented generation system using LangChain, Pinecone vector store, and Python. Install dependencies,…
This guide shows you how to adapt a 8B parameter Llama 3 model for a specific task using Low-Rank Adaptation (LoRA) on a…