Sharing AI/ML ideas one python notebook at a time – Yasu Flores

Training a GPT-like transformer with different graphics cards using Vast.ai servers

transformers

neural

networks

machine

learning

GTX

graphics cards

The plan was to create an analysis of how fast you can train a GPT-like neural network and compare different GPUs and how quick each one of them trains a neural network like…

Receipt parsing - A comparison between a small and a medium sized model

vision

ml

ai

jpg

png

image recognition

granite

smol

docling

In this post, I’ll go over the comparison of 2 models in the task of retrieving the total out of a receipt from a purchase.

How to recreate Navan’s receipt scan feature to retrieve the total amount

vision

ml

ai

jpg

png

image recognition

smol

smoldocling

Using the SmolDocling-256M vision model to parse receipt totals, replicating Navan’s receipt scan feature with 80% accuracy across five real-world receipts.

How to create an engineering team that hits their deadlines

leadership

engineering

deadlines

software

product

Does this sound familiar?:

Python RAG Tutorial with Pinecone and local Ollama

rag

python

pinecone

retrieval

augmentation

We’ll walk through a basic RAG example for any project using Python and Flask. By the end of this tutorial you will have a working RAG setup to start experimenting with.

AlphaEvolve told Google to avoid using Machine Learning to optimize server utilization

ml

ai

model

evaluation

agi

google

alphaevolve

funsearch

science

math

Google’s AlphaEvolve is an impressive product and idea. The idea is that it spawns several LLM threads and it orchestrates them to generate scientific advancements and it…