machine-learning

Fine-tune a local LLM on your own chat history to mimic how you write — an AI doppelganger / digital-twin toolkit built on LLaMA-Factory (LoRA SFT).

Having fun with ML

template for duplicating and executing Hugging Face Spaces either on SM Studio Lab, Google Colab, or locally.

AI-powered emotion detection & personalized recommendations using NLP and machine learning

Code and dataset for paper - Application of Deep Learning in Generating Structured Radiology Reports: A Transformer-Based Technique

Use Transformers.js from Blazor WebAssembly to run pretrained models with the ONNX Runtime in the browser.

Engineered an advanced deep learning model to automate the classification of financial documents, including Balance Sheets, Cash Flow and Income Statements using Bidirectional LSTM and TensorFlow. The model achieved an impressive accuracy of 96.2%, enhancing efficiency and reducing errors in document management for the finance and banking sectors.

Retreival Augmented Generation (RAG) chatbot for my blog

AI-powered compliance analysis engine for civil engineering that automatically validates Brazilian Technical Standards (NBRs), saving engineers 30% of their time by eliminating manual document verification while preventing structural failures and regulatory fines.

Persistent semantic memory server for MCP - Give your AI long-term memory that survives across conversations. Lightweight Python server with SQLite storage and semantic search.

LanceDB C# SDK

The blazingly fast in-memory vector database 🚀

High-performance Holographic Memory System (HMS) for Node.js, powered by Rust. This library implements Vector Symbolic Architectures (VSA) using Binary Spatter Code (BSC) to enable semantic search, analogical reasoning, and associative memory at scale.

🧠 | Multimodal Integration of Oncology Data System

FiftyOne Plugin for searching images by audio clip using ImageBind and Qdrant

Professional CLI toolkit for Modal GPU workflows, Docker Compose deployments, Python runtimes, model serving, and account/billing management.

Open-source framework for turning expert knowledge into PII-free synthetic conversational data and production-ready LoRA adapters.

Complete setup guide for a 2-node NVIDIA DGX Spark cluster — distributed training, CUDA inference with EXO, NCCL tuning for Grace Blackwell, NVMe-TCP shared storage, and 200 Gb/s direct fabric networking.

Taller: Modelos de lenguaje a tu medida. 2º Workshop Argentino de NLP, Córdoba 2023

A deep learning project for detecting and classifying teeth as normal or cavity using YOLOv12m. The model is integrated into a web application for real-time dental screening. Designed to enhance early diagnosis accessibility, with future improvements planned for dataset expansion, annotation quality, and robustness to real-world conditions.