Skip to content
View Basearchio's full-sized avatar

Block or report Basearchio

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Basearchio/README.md

👋 Hi, I'm Basearchio

I build software that automates repetitive work and improves reliability.

I use AI as an engineering partner to design, build, and validate practical software that solves real-world problems.


🎯 Focus

  • ⚙️ Automation
  • 🤖 AI-assisted Software Development
  • 📊 Data Analysis & Integrity
  • 🪟 Windows Tooling
  • 🧠 Local LLM Workflows

🛠️ Tech

Languages & Scripting

Python

Tools & Technologies

LLM Automation


🚀 Featured Projects

One-click Windows launcher for PrismML-Eng/Bonsai-demo.

  • Automated installation and local LLM setup
  • Interactive model selection
  • Windows Batch & PowerShell automation
  • Software Requirements Specification (SRS)

A resilient web scraping framework focused on reliable and maintainable data collection.

  • Structured scraping workflow
  • Automated data collection
  • Fault-tolerant execution
  • Reusable scraping components

Experimental framework for verifying low-bit quantization equivalence in Qwen2.5-VL models.

  • Adaptive temperature-based sampling
  • Model-specific normalization
  • Quantization benchmarking
  • Automated evaluation reports

🧠 Philosophy

Most of my projects begin with one question:

"What caused the problem, and how can the structure be improved so it never happens again?"

I enjoy analyzing workflows, identifying root causes, and turning repetitive, error-prone processes into reliable software.

Pinned Loading

  1. Sovereign-Scraper Sovereign-Scraper Public

    A local-first, self-healing web scraper that extracts structured data through browser-rendered page analysis. Works without LLMs, with optional AI-powered semantic labeling and recovery.

    Python

  2. quant-squeeze quant-squeeze Public

    Experimenting whether low-bit quantized VLMs can match high-bit ones via repeated sampling + normalization ("squeeze and normalize").

    Python

  3. Easy-bonsai Easy-bonsai Public

    One-click Windows setup & launcher for PrismML Bonsai-demo — pick a model, everything else is automated.

    Batchfile 1