FAQ

Common questions answered

Is Hugging Face Transformers free to use?

Yes, the Hugging Face Transformers library is open source and free to use under the Apache 2.0 license. However, some additional services like hosted inference APIs may have associated costs.

Which deep learning frameworks does it support?

Hugging Face Transformers supports PyTorch, TensorFlow, and JAX, allowing users to choose the backend that best fits their needs.

Can I fine-tune models on my own data?

Absolutely. The library provides tools such as the Trainer API to fine-tune pre-trained models on custom datasets with minimal code.

How large are the models and what are the hardware requirements?

Model sizes vary from tens of megabytes to several gigabytes depending on architecture and size. Running large models typically requires GPUs for efficient training and inference.