Ahmadzei's picture
added 3 more tables for large emb model
5fa1a76
It should look as follows:
python
model = BrandNewBertModel.from_pretrained("/path/to/converted/checkpoint/folder")
input_ids = [0, 4, 4, 3, 2, 4, 1, 7, 19]
output = model(input_ids).last_hidden_states
It is very likely that the 🤗 Transformers implementation and the original model implementation don't give the exact
same output the very first time or that the forward pass throws an error.