Fine-Tuning Made Fast: A Quick Guide to Unsloth 馃Ε
Aug 5, 2025 路 3 min read 路 Fine-tuning large language models (LLMs) is no longer just for big tech companies. Thanks to Unsloth, you can train your own AI models鈥攓uickly and efficiently鈥攐n modest hardware like Google Colab or your local RTX GPU. In this article, we鈥檒l walk thr...
Join discussion
Turn Any AI Into Your Personal Assistant: Fine-Tune LLMs Without Coding Experience
Jul 27, 2025 路 4 min read 路 Ever dreamed of having your own personalized AI assistant? One that understands your specific domain, speaks your language, and adapts to your unique needs? What if I told you that you could create one using nothing but free tools and a few hours of ...
Join discussion
Deploying Gemma 1B GGUF model with llama.cpp on Ubuntu
Mar 23, 2025 路 5 min read 路 For this guide we should be using an Ubuntu server with atleast 2 GiB of GPU VRAM, 2 VCPU Cores, 8 GiB RAM, and 50 GiB of storage. Let鈥檚 start by updating and installing necessary libraries. sudo apt update && sudo apt upgrade -y sudo apt install -y ...
Join discussion
Fine tune Llama 70B using Unsloth, LoRA & Modal as easy as OpenAI ChatGPT
May 26, 2024 路 7 min read 路 Intro I came across Modal last summer when I was on a self-inspired mission to run BLOOM 176B model as an open-source competition to ChatGPT. The guys at modal were amazing and after several days of tinkering after my work, I got it up using 6 GPUs s...
Join discussion