PinnedPublished inNeural BitsHow to ensure your deep learning stack is fail-safe in production?Build an end-to-end monitoring dashboard using Prometheus, Triton, and Grafana.Apr 11, 20243Apr 11, 20243
PinnedPublished inNeural BitsA Kickstart in Deep Learning Real-Time Video ProcessingA guide to get you started, learn about video formats, HTTP, WebSockets and WebRTC streaming with Python.May 9, 20243May 9, 20243
PinnedBest practices when evaluating fine-tuned LLMs.How to evaluate a custom fine-tuned model, leveraging GPT3.5-Turbo, custom qualitative evaluation templates while monitoring prompts and…May 26, 20242May 26, 20242
PinnedHow to fine-tune LLMs on custom datasets at Scale using Qwak and CometMLHow to fine-tune a Mistral7b-Instruct using PEFT & QLoRA, leveraging best MLOps practices deploying on Qwak.ai and tracking with CometML.May 18, 20242May 18, 20242
PinnedPublished inDecoding MLHow to build a Real-Time News Search Engine using Serverless Upstash Kafka and Vector DBA hands-on guide to implementing a live news aggregating streaming pipeline with Apache Kafka, Bytewax, and Upstash Vector Database.Apr 13, 20247Apr 13, 20247
The LLM-Twin Free Course on Production-Ready RAG pipelines.Learn how to build a full end-to-end LLM & RAG production-ready system. Learn about and code along each component in a hands-on fashion.Jun 15, 20243Jun 15, 20243
How to evaluate your RAG using RAGAs FrameworkHow to evaluate your RAG, following the best industry practices using the RAGAs framework. Learn about Retrieval & Generation…Jun 10, 20242Jun 10, 20242
Published inNeural BitsMaster ML configuration files using OmegaConf and HydraHow to handle complex configurations without changing code.Apr 18, 20241Apr 18, 20241
Published inNeural BitsEnhancing data processing workflows with Pydantic ValidationsUse Pydantic models and field validators to ensure consistency in your data models like a PRO.Apr 9, 2024Apr 9, 2024
The end-to-end PyTorch to TensorRT pipeline for YOLO models you must know about.The challenge of serving deep learning models in production environments. A pipeline to optimize and serve TensorRT engines for YOLO Object…Feb 23, 20241Feb 23, 20241
