8b + Unsloth 2x faster - Colab

unsloth  thank you so much!!! from unsloth import FastLanguageModel from _templates import get_chat_template model, tokenizer = FastLanguageModel  We're thrilled to unveil two major upgrades to MonsterTuner, designed to supercharge your LLM fine-tuning: Unsloth and Scaled Dot-Product

By manually deriving all compute heavy maths steps and handwriting GPU kernels, unsloth can magically make training faster without any hardware changes  Unsloth - 5X faster 50% less memory LLM finetuning Visual Studio Code

Unsloth - 5X faster 50% less memory LLM finetuning Visual Studio Code fine tune on a small dataset using unsloth & colab