Contact Us

Please reach out to us on twitter: @hipatic

Email: admin (at) hipatic.com (Replace (at) by @ and remove spaces.)

Popular posts from this blog

Run Visual Studio Code Natively on Termux Proot Ubuntu or Other Linux Distribution

 I recently got back to Android because I came across an article on installing Ubuntu "natively" on Android without systemd via Termux and proot. I will link relevant articles as I update this post. After I installed Ubuntu via proot, I searched for ways to get a GUI running. This can be done via VNC Server. Again, I will link relevant articles later. Then, I looked for ways to get VS Code running and found that most guides propose installing code-server and then accessing Code via a browser, which has some limitations with extensions. I would propose using vscode.dev instead if you generally have a good network connection on your phone. Because I had a gui running from step 2, I installed VS Code as you would normally on Ubuntu (from a .deb file or using the tar.gz file available for download for arm64 on the VS code website. I realised that I could not install .deb files on a stripped down Ubuntu environment (it worked when I installed ubuntu-desktop instead of gnome deskto...
Read more

Quantization for Small Models: A Practical, Reproducible Guide

Quantization for Small Models: A Practical, Reproducible Guide This article outlines a clear, reproducible workflow for applying quantization to small language models. The objective is to reduce memory usage, improve inference efficiency, and retain acceptable accuracy on constrained hardware. Purpose Quantization converts model weights from floating-point formats (fp32 or fp16) into lower-precision representations such as int8 or int4. This reduces VRAM and RAM consumption and enables running larger models on limited devices without modifying model architecture. Scientific Basis Quantization reduces the numeric precision of weights while preserving structural relationships. 4-bit methods apply additional techniques (double quantization, grouped quantization) to minimize accuracy loss. Inference is feasible because many transformer components are resilient to reduced precision. When to Use Quantization Scenario Suitability Running models on 4–8 GB GPUs Highly s...
Read more

Windows 8 Developer Preview on Acer Aspire One AOA150

Image
Update November 1st 2012: Windows 8 on Acer Aspire AOA 150 Update: October 31st 2012 Since posting this article about over a year ago, the said AOA 150 is still alive, although with some changes. I have added a 500gb 7200 rpm HDD(ST9500420ASG) to the netbook. The netbook now runs a Windows 8 Release Preview with Ubuntu 12.10 as the main OS.  Windows 8 Release Preview apparently runs faster than Developer Preview. I might buy an upgrade license to Windows 8 pro, but with a resolution of 1024x600 and metro(windows 8) apps not working, I don't see much point. But I do need something to run my Nokia Music on... Other updates on Windows 8 1. License types available for Windows 8:   a. Upgrade License - $39.99 till January 31 2013   b. OEM License (The license which vendors will use when they bundle Windows 8 with your new PC)   c. System Builder License (Similar to the OEM license, but you can purchase this to build your own PC. Single PC/Virtual Environment u...
Read more