link
LFM2.5-230M is a promising option for fine-tuning to translate natural language instructions into a series of tool calls. www.liquid.ai/blog/lfm2-5-...
LFM2.5-230M: Built to Run Anywhere — BlogAbout Me
I’m a Senior Python Dev, AI Enthusiast, Builder. These are some of the things I’m working on:
- Teaching Python through bite-sizes lessons wrapped in a Koan.
Blog Posts
Nov 16, 2025
Skip the fork
May 1, 2025
Building your own tools
Latest Notes
link
Drop-in replacement for whisper.cpp supporting STT with lots of different model families. I also appreciate that all the models were tested to compare WER. github.com/handy-comput...
https://github.com/handy-computer/transcribe.cpp
link
A two-stage privacy filter that runs completely on-device. First stage is a set of regex rules, second stage is a 14Mb MiniLM model fine tuned on the OpenPII dataset. This is where we need to be headed. ndstudio.gov/posts/say-he...
Introducing RampartProjects
These are some of my projects
Find Substack
Discover quality Substack posts. Beat the notes slop.
#Substack
#Discovery
#Newsletter
#Content
Python Koans
Python lessons wrapped in koans. A weekly newsletter.
#Python
#Education
#TDD
#Learning
