How to use NewT5SharedHeadsSharedKeyValues/t5-efficient-tiny-skv with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-tiny-skv") model = AutoModelForSeq2SeqLM.from_pretrained("NewT5SharedHeadsSharedKeyValues/t5-efficient-tiny-skv", device_map="auto")
2935ffd
1
2
3
4
5
6
7
8
9
--- tags: - t5-new-hf-not-loaded --- # Test Hf T5: MTF T5: -138.18275451660156
