Sorry if this is a silly question, but I cant seem to find any proper solution to this.
I am using transformers==2.8.0
and have fine-tuned a gpt2
model with my own dataset. I know that during training it creates checkpoints in pytorch and that can be used for text generation, but I want to save/load model in tensorflow.
I know that TFGPT2LMHeadModel
exists and that it can be used, but I havent found an example online doing this.
Can someone help me please? How can I export a fine-tuned model into tensorflow, so that I can then generate text using that model?
Thanks