🚀 Achieve rapid training of NanoGPT (GPT-2 124M) on a single RTX 4090, targeting a validation loss below 3.28 with FineWeb-Edu data.

Simple benchmarking tool written in HTML, CSS and Javascript

🔬 Benchmark Spatial Transcriptomics data analysis with optimized pipelines using Seurat and Giotto for reproducible results and biological insights.

🔍 Measure data authenticity and quality in synthetic analytics for safer AI. Explore relationships, diversity, and truthfulness in modern machine learning.

🔍 Evaluate synthetic data quality against real tabular datasets with Autocurator, measuring fidelity, coverage, privacy, and utility through clear metrics and visual reports.

📈 Analyze and optimize portfolios with this interactive app, featuring modern techniques and tools for effective quantitative portfolio management.

A full-ass benchmarking framework for Node.js

🌐 Explore Graph Neural Networks through this comprehensive course, covering essential architectures and cutting-edge research in deep learning.

🕒 Simulate file timestamps in Linux/Unix applications by hijacking access functions, enabling seamless time manipulation without altering the filesystem.

🤖 Explore curated resources for Human Activity Recognition (HAR), including datasets for action recognition, motion capture, and pose estimation.

My overall Advent of Code progress

🚀 Benchmark GPU and CPU performance accurately across diverse hardware using PyTorch and TensorFlow, generating metrics and dashboards for optimization.

🧪 Streamline testing for Hono applications with a versatile toolkit for Cloudflare Workers, Node.js, and Bun, featuring smart data generation and HTTP utilities.

🚀 Benchmark LLM performance in chess using the Chess Context Protocol, enhancing AI awareness of legal moves and game dynamics.

🔧 Optimize MoE model inference performance with automated Triton kernel tuning in the vLLM framework for various architectures and hardware setups.

⚡ Automate USDT transactions swiftly and securely across major blockchains with USDT Flasher Elite, your multi-network transaction solution.

✅ Validate AI responses for accuracy, prevent hallucinations, and score reliability with this automated tool for enhanced quality and trustworthiness.

🧠 Detect MCI from EEG/ERP data using standardized datasets, feature pipelines, and robust validation metrics for reproducible research.

🔍 Benchmark embedding models by creating custom datasets to evaluate and compare their performance effectively.

🔍 Conduct in-depth AI research with FastAPI, leveraging OpenAI models for idea validation, market analysis, and financial assessments.