view post Post 5363 fine-tuning a 14B model with TRL + SFT on a free Colab (T4 GPU)?thanks to the latest TRL optimizations, you actually can!sharing a new notebook showing how to do it 😎colab: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_trl_lora_qlora.ipynbnotebooks in TRL: https://github.com/huggingface/trl/tree/main/examples/notebooks See translation 2 replies · 🔥 14 14 👍 2 2 + Reply