How to use NewT5SharedHeadsSharedKeyValues/t5-efficient-base-sh with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-base-sh") model = AutoModelForSeq2SeqLM.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-base-sh")
Hf T5: -95.86687088012695 MTF T5: -67.8558578491211
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-base-sh") model = AutoModelForSeq2SeqLM.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-base-sh")