All articles tagged with #lora
Open-source ExpressLRS receivers built around an ESP32 and SX1281 demonstrate long-range drone control at 2.4 GHz using Chirp Spread Spectrum modulation, maintaining links over more than five kilometers even through a forest. Four receivers (two with additional 900 MHz antennas) showcase the system’s reliability thanks to CSS’s ~24 dB gain and inverse-chirp decoding via FFT, building on LoRa technology for extended reach.
Hackaday reports on a project where Meshtastic is used beyond simple text messaging: an off-grid, long-range mesh connects a shed alarm to Home Assistant via Heltec ESP32 LoRa modules. A remote node watches an infrared beam and publishes alerts over Meshtastic, while a second module bridges to Wi‑Fi and MQTT for Home Assistant integration, showcasing Meshtastic’s potential for distributed sensing and automation beyond chat."
Fine-tuning large language models (LLMs) like Mistral 7B at home is now more feasible thanks to techniques like Low Rank Adaptation (LoRA) and its quantized variant QLoRA, which reduce the computational and memory requirements. This guide explores the process of fine-tuning to modify a model's behavior or style using a single GPU, highlighting the importance of data preparation and the impact of hyperparameters. While fine-tuning is resource-intensive, it offers a way to customize models beyond what retrieval augmented generation (RAG) and prompt engineering can achieve.