using new run, 70k checkpoint (should be the same but this guarantees) 35243e0
Brendan King commited on
How to use Brendan/meta-baseline-t5-small with Transformers:
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Brendan/meta-baseline-t5-small")
model = AutoModelForSeq2SeqLM.from_pretrained("Brendan/meta-baseline-t5-small", device_map="auto")