Post
144
New GRPO + TRL free Colab notebook out! ๐ฅ
Fine-tune 7B+ models on T4 GPUs thanks to a ton of memory optimizations for GRPO
7B model uses only 9.2 GB VRAM (~7ร reduction) ๐คฏ
Try the notebook here ๐ https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_trl_lora_qlora.ipynb
Fine-tune 7B+ models on T4 GPUs thanks to a ton of memory optimizations for GRPO
7B model uses only 9.2 GB VRAM (~7ร reduction) ๐คฏ
Try the notebook here ๐ https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_trl_lora_qlora.ipynb
