How to use NewT5SharedHeadsSharedKeyValues/t5-efficient-tiny-skv with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-tiny-skv") model = AutoModelForMultimodalLM.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-tiny-skv")
Hf T5: MTF T5: -138.18275451660156
