Show HN: Mistral NeMo finetuning fits in Colab https://bit.ly/3Y5Ye5b

Show HN: Mistral NeMo finetuning fits in Colab Managed to make Mistral NeMO 12b https://bit.ly/3zM6vBg fit in a free Google Colab with a Tesla T4 GPU (16GB) for 4bit QLoRA finetuning! Managed to shave 60% VRAM usage and made it 2x faster as well! It should work in under 12GB of VRAM as well! https://bit.ly/3WwRY4b July 19, 2024 at 05:36PM