TGTGInsighttelegram intelligenceLIVE / telegram public index
← GitHub Trends

TGINSIGHT SIMILAR POSTS

Find similar content

Source channel @githubtrending · Post #14845 · Jun 20

#jupyter_notebook#ai#artificial_intelligence#chatgpt#deep_learning#from_scratch#gpt#language_model#large_language_models#llm#machine_learning#python#pytorch#transformer You can learn how to build your own large language model (LLM) like GPT from scratch with clear, step-by-step guidance, including coding, training, and fine-tuning, all explained with examples and diagrams. This approach mirrors how big models like ChatGPT are made but is designed to run on a regular laptop without special hardware. You also get access to code for loading pretrained models and fine-tuning them for tasks like text classification or instruction following. This helps you deeply understand how LLMs work inside and lets you create your own functional AI assistant, gaining practical skills in AI development[1][2][3][4]. https://github.com/rasbt/LLMs-from-scratch

Results

1 similar post found

Search: #vesc

当前筛选 #vesc清除筛选
Libreware

@libreware · Post #1581 · 04/24/2026, 02:58 PM

Scooter Knowledge Base https://github.com/firebl0od/Scooter_Knowledge/tree/main This repository collects and organizes information about electric scooter setup, maintenance, and troubleshooting. The primary source material is a large Telegram conversation exported from the "VESC help" group https://t.me/VescHelpGroup. The goal of the project is to extract practical knowledge from the chat logs and document it in a structured, reusable format. VESC is short for Vedder Electronic Speed Controller. It is an open-source, open-hardware motor speed controller that allows for advanced customization via software (such as the VESC Tool app). It is commonly used in electric scooters, skateboards, electric bicycles, and robotics projects to provide precise control, regenerative braking, and sensorless operation, overcoming the limitations of standard closed controllers. The knowledge/processed/themes/ directory contains 72 professionally formatted documents covering: 28 brand dossiers covering controllers, motors, and BMS systems from manufacturers like Spintend, Flipsky, Makerbase, 3Shul, and more 44 comprehensive guides including: VESC tuning and parameter optimization Battery pack design and BMS integration Motor cooling and thermal management Conversion guides for popular scooter models (Ninebot, Xiaomi, etc.) Brake upgrades and maintenance Field weakening and high-voltage setups Diagnostic tools and troubleshooting All documents use a consistent, readable format with: Clean footnote citations linking back to source material Well-organized sections with proper headings Tables and checklists for quick reference Preserved technical accuracy from the original discussions #electric#scooter#bike#controllers#vesc#batteries#diy