Razvant Alexandru – Medium

Razvant Alexandru

Pinned

Razvant Alexandru
in
Decoding ML

How to evaluate your RAG using RAGAs Framework

How to evaluate your RAG, following the best industry practices using the RAGAs framework. Learn about Retrieval & Generation…

Jun 10

How to evaluate your RAG using RAGAs Framework

Jun 10

Pinned

Razvant Alexandru
in
Decoding ML

Best 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

Best practices when evaluating fine-tuned LLMs.

May 26

Pinned

Razvant Alexandru
in
Decoding ML

How to fine-tune LLMs on custom datasets at Scale using Qwak and CometML

How to fine-tune a Mistral7b-Instruct using PEFT & QLoRA, leveraging best MLOps practices deploying on Qwak.ai and tracking with CometML.

May 18

How to fine-tune LLMs on custom datasets at Scale using Qwak and CometML

May 18

Pinned

Razvant Alexandru
in
Decoding ML

How to build a Real-Time News Search Engine using Serverless Upstash Kafka and Vector DB

A hands-on guide to implementing a live news aggregating streaming pipeline with Apache Kafka, Bytewax, and Upstash Vector Database.

Apr 13

How to build a Real-Time News Search Engine using Serverless Upstash Kafka and Vector DB

Apr 13

Razvant Alexandru
in
Decoding ML

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

The LLM-Twin Free Course on Production-Ready RAG pipelines.

Jun 15

Razvant Alexandru
in
Decoding ML

A Kickstart in Deep Learning Real-Time Video Processing

A guide to get you started, learn about video formats, HTTP, WebSockets and WebRTC streaming with Python.

May 9

A Kickstart in Deep Learning Real-Time Video Processing

May 9

Razvant Alexandru
in
Decoding ML

Master ML configuration files using OmegaConf and Hydra

How to handle complex configurations without changing code.

Apr 18

Master ML configuration files using OmegaConf and Hydra

Apr 18

Razvant Alexandru
in
Decoding ML

How 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

How to ensure your deep learning stack is fail-safe in production?

Apr 11

Razvant Alexandru
in
Decoding ML

Enhancing data processing workflows with Pydantic Validations

Use Pydantic models and field validators to ensure consistency in your data models like a PRO.

Apr 9

Enhancing data processing workflows with Pydantic Validations

Apr 9

Razvant Alexandru
in
Decoding ML

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

The end-to-end PyTorch to TensorRT pipeline for YOLO models you must know about.

Feb 23

Razvant Alexandru

Razvant Alexandru

Senior ML Engineer | Generative AI | MLOps. Leveraging AI systems to production! | 🔗 Join 6.5k+ engineers at Decoding ML https://decodingml.substack.com

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams