DeCLUTR icon indicating copy to clipboard operation
DeCLUTR copied to clipboard

Models don't load with allennlp>=1.2.0

Open JohnGiorgi opened this issue 4 years ago • 2 comments

The pretrained models do not load properly with allennlp>=1.2.0. The error reported is:

RuntimeError: Error loading state dict for DeCLUTR
    Missing keys: []
    Unexpected keys: ['_text_field_embedder.token_embedder_tokens.transformer_model.roberta.pooler.dense.weight', '_text_field_embedder.token_embedder_tokens.transformer_model.roberta.pooler.dense.bias']

For now, I will constrain the dependency to be "allennlp>=1.1.0, <1.2.0", but it would be great to find another solution (short of re-training the model).

JohnGiorgi avatar Nov 11 '20 23:11 JohnGiorgi

This problem is solved by migrating to AllenNLP>=2.0.0. I will close this once I have merged the migration and re-trained the models.

JohnGiorgi avatar Feb 16 '21 20:02 JohnGiorgi

Also see: https://github.com/allenai/allennlp/pull/4621#issuecomment-690782222

Which may allow us to avoid re-training

JohnGiorgi avatar Mar 03 '21 18:03 JohnGiorgi