PEFT: Parameter-Efficient Fine-Tuning of Billion-Scale Models on Low-Resource Hardware

Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of pre-trained language models (PLMs) to various downstream applications without fine-tuning all the model's paramete

PEFT позволяют добиться высокой производительности моделей на слабом железе, с небольшым количество обучаемых данных, .

🖥 Github: https://github.com/huggingface/peft

💨 Hugging Face: https://huggingface.co/blog/peft

🖥 Colab: https://colab.research.google.com/drive/1jCkpikz0J2o20FBQmYmAGdiKmJGOMo-o

👉 @bigdata_1