How to use NewT5SharedHeadsSharedKeyValues/t5-efficient-large-skv with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-large-skv") model = AutoModelForSeq2SeqLM.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-large-skv")
Hf T5: MTF T5: -59.432472229003906
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-large-skv") model = AutoModelForSeq2SeqLM.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-large-skv")