Hello everyone,
I’m relatively new to using Hugging Face and I have a question regarding using the Inference API. In my repository, I have both a PyTorch model and a TensorFlow model, each trained differently. However, I want to target only my TensorFlow model when using the Hugging Face Inference API because i am more focused train my latest model version in tensorflow and my pytorch model is obsolete. Can anyone guide me on how to achieve this?
I’ve explored the documentation, but I’m still unsure about how to specify the target model, especially when dealing with multiple models in the same repository. Should I modify the configuration file or adjust the code somehow?
Any help or pointers in the right direction would be greatly appreciated. Thank you in advance!