How to use google/switch-large-128 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/switch-large-128") model = AutoModelForSeq2SeqLM.from_pretrained("google/switch-large-128")
The decoder_start_token_id has been forgotten for this model as well.
· Sign up or log in to comment