Tag archive
Add LoRa Long-Range Radio: Send sensor data up to 15km from a Raspberry Pi Pico with a plug-in LoRa module and a LiPo battery. A cheap weekend build for off-grid IoT.
LoRA isn't a discount version of full fine-tuning— it's a different optimization landscape, and preference optimization exposes exactly why that disti
A practical 2026 guide to fine-tuning open-source LLMs with LoRA and QLoRA using Unsloth + Gemma 4 — including GPU requirements, hyperparameter defaults, evaluation setup, and when to just prompt instead.
When you continually pre-train an LLM into a 'world model', it quietly forgets general knowledge — and a little data mixing buys most of it back. But how much it forgets depends heavily on how you specialize it, and full fine-tuning pays three costs a single benchmark undersells.
Video Tutorial Watch first if you want to see the projects in action. Long Version: ...
Video Tutorial (Optional) Watch first if you want to see Heltec V3 LoRa boards sending GPS...
A new paper, Program-as-Weights, uses a 4B compiler to turn natural-language specs into small neural adapters that let a 0.6B model match a 32B model on fuzzy tasks, running at about 30 tokens per second on a laptop.
Project Overview ESP32-S3 + NEO-6M + SX1262: Build a no-SIM LoRa GPS tracker where an...
Project Overview Arduino + LoRa (RFM98/Ra-02) vs NRF24L01+: This guide helps you choose...
SIA by Hexo Labs co-evolves agent scaffold and LoRA weights in one loop, selecting PPO, GRPO, or EAW per reward shape. Hands-on walkthrough
A practical walkthrough of LoRA and QLoRA -- how low-rank adaptation works, what NF4 quantization brings, and when to use each.