How to use GeneZC/bert-large-mnlimm with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, BertCls tokenizer = AutoTokenizer.from_pretrained("GeneZC/bert-large-mnlimm") model = BertCls.from_pretrained("GeneZC/bert-large-mnlimm", device_map="auto")
bert-large-uncased finetuned on MNLI-mm.
bert-large-uncased
MNLI-mm
batch size is 32, learning rate is 2e-5.
acc: 0.8613
