I’m trying to run EsperBERTo example in Colab to train model and tokenizer from scratch. When recreating tokenizer in transformers, I get “file ./EsperBERTo/config.json not found” sort-of message , that I saw discussed earlier in another topic here:
“How to train a new language model from scratch using Transformers and Tokenizers” possibly requiring an update
I’ve tried to follow the solution from the aforementioned topic, but it didn’t help. Could someone please tell me how to avoid the issue?