How to use NewT5SharedHeadsSharedKeyValues/t5-efficient-xl-sh with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-xl-sh") model = AutoModelForSeq2SeqLM.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-xl-sh")
Hf T5: -118.6875057220459 MTF T5: -76.85459899902344
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-xl-sh") model = AutoModelForSeq2SeqLM.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-xl-sh")