AI SO Sonal Mishra I Fine-Tuned a 1.1B Training only 0.5% of weights was the easy part. Knowing what to measure was the hard part.
AI JO jon allen LLM “repeat curse” — a feature or errant condition LLM that loops on a word or set of phrases.
AI TCH SPT PR Praveen Kusuma 2 ways to run Ollama DeepSeek Locally — Using Docker and Directly on Local Machine Artificial Intelligence is the most happening technology in the world today. Ever dreamed of having your own personal LLM all running on…
AI SPT AD Aditya Pawar How I Got LLMs Running Locally (CPU and GPU Guide) The Backstory: Running LLMs on My Own PC
AI SH Shreyahs Building a Local AI Chatbot using FastAPI, Ollama & TinyLLaMA “Why just use ChatGPT when you can build your own local chatbot?”
AI IM Immanuel Leon Salomo Sihombing Building a simple Local Chat-Bot UI with LLM integration — My Beginner Project Introduction
HUM AI DE Deepesh Sharma Fine-Tuning LLMs with LoRA and QLoRA: From Confusion to (Kinda) Working Results It all started with a simple thought — in today’s AI world, why are teachers still manually making quiz papers and surprise tests like…
AI TCH BH Bhagya Rana 🧠 Beyond GPT: How Small Language Models Are Taking Over Edge Devices The Rise of Lightweight, Privacy-Friendly AI Models for Local Inference on Phones, Raspberry Pi, and IoT Devices
AI HUM NE Nedved Yang · The Constellar Digital&Technology Blog Geek Out Time: LLM Inference Exposed-How It Works And How to Make It Fast on Google Colab In recent months, the race to run Large Language Models (LLMs) faster and cheaper has accelerated — and not just for training. Inference…
AI MDA DE Dedi Hartono Fine-Tuning TinyLLaMA (1.1B) untuk Mengubah Deskripsi Teks Menjadi Warna Fine-tuning adalah proses melatih kembali model AI yang sudah dilatih sebelumnya (pretrained model) dengan data baru yang lebih spesifik…
ART AI SU Sumit Singh Fine-Tuning TinyLlama and Phi-2: Fails, Fixes, and Pirate Chatbot A hands-on journey of fine-tuning TinyLlama and Microsoft’s Phi-2 for chat-style output using LoRA. Lessons learned, errors debugged, and a…