How to resolve coreferences without Internet using AllenNLP and coref-spanbert-large?

[Daisy-a-p]

I want to resolve coreferences without Internet using AllenNLP and coref-spanbert-large model. I try to do it in the way that is describing here https://demo.allennlp.org/coreference-resolution

As I understood, firstly I need to download a transformer model spanbert-large-cased.
I did it and saved to folder transformer_model_name the path which I mention in code.

Here is my code:

import allennlp_models.tagging
from transformers import AutoConfig, AutoTokenizer`

tokenizer = AutoTokenizer.from_pretrained(r"C:\Users\aap\Desktop\spanbert-large-cased")
config = AutoConfig.from_pretrained(r"C:\Users\aap\Desktop\spanbert-large-cased")
local_config_path = r"C:\Users\aap\Desktop\spanbert-large-cased\span"
tokenizer.save_pretrained(local_config_path)
config.to_json_file(local_config_path + "/config.json")`


predictor = Predictor.from_path(
    r"C:\Users\aap\Desktop\coref-spanbert-large-2021.03.10.tar.gz",
    overrides={
        "dataset_reader.token_indexers.tokens.model_name": local_config_path,
        "validation_dataset_reader.token_indexers.tokens.model_name": local_config_path,
        "model.text_field_embedder.tokens.model_name": local_config_path,
    },
)

example = '''
Paul Allen was born on January 21, 1953, in Seattle, Washington, to Kenneth Sam Allen and Edna Faye Allen.\
     Allen attended Lakeside School, a private school in Seattle, where he befriended Bill Gates, two years younger,\
      with whom he shared an enthusiasm for computers.
'''
pred = predictor.predict(document=example)
coref_res = predictor.coref_resolved(example)
print(pred)
print(coref_res)

Despite mentioned path to files local_config_path it seems it tries to load files from other folder C:\Users\aap/.cache\huggingface\transformers

Here is traceback:

C:\Users\aap/.cache\huggingface\transformers
C:\Users\aap/.cache\huggingface\transformers\1a1dfe6956710e7344f6fc7595b16b878615c5f6f2b91e9699f6c8787af0d2fb
C:\Users\aap/.cache\huggingface\transformers
C:\Users\aap/.cache\huggingface\transformers\47c606d9dcccc6b316f18beea908fad9eccfec6213d9a8ea31e366fc4233934d
Some weights of BertModel were not initialized from the model checkpoint at SpanBERT/spanbert-large-cased and are newly initialized: ['bert.pooler.dense.weight', 'bert.pooler.dense.bias']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
C:\Users\aap/.cache\huggingface\transformers
C:\Users\aap/.cache\huggingface\transformers\1a1dfe6956710e7344f6fc7595b16b878615c5f6f2b91e9699f6c8787af0d2fb
C:\Users\aap/.cache\huggingface\transformers
C:\Users\aap/.cache\huggingface\transformers\1863c6e5ed20880e869aedeb4d0866efd2bec702a76279326207bc20919a2718
C:\Users\aap/.cache\huggingface\transformers
C:\Users\aap/.cache\huggingface\transformers\045335998d9d6b719426253efa717597f33ae6c1edf4d9fd858cd2d88297ad35
Traceback (most recent call last):
  File "C:/Users/aap/Desktop/CoreNLP/Coref_AllenNLP.py", line 29, in <module>
    "validation_dataset_reader.token_indexers.tokens.model_name": local_config_path,
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\predictors\predictor.py", line 361, in from_path
    load_archive(archive_path, cuda_device=cuda_device, overrides=overrides),
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\models\archival.py", line 208, in load_archive
    model = _load_model(config.duplicate(), weights_path, serialization_dir, cuda_device)
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\models\archival.py", line 246, in _load_model
    cuda_device=cuda_device,
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\models\model.py", line 406, in load
    return model_class._load(config, serialization_dir, weights_file, cuda_device)
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\models\model.py", line 305, in _load
    vocab=vocab, params=model_params, serialization_dir=serialization_dir
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 604, in from_params
    **extras,
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 632, in from_params
    kwargs = create_kwargs(constructor_to_inspect, cls, params, **extras)
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 200, in create_kwargs
    cls.__name__, param_name, annotation, param.default, params, **extras
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 307, in pop_and_construct_arg
    return construct_arg(class_name, name, popped_params, annotation, default, **extras)
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 341, in construct_arg
    return annotation.from_params(params=popped_params, **subextras)
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 604, in from_params
    **extras,
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 632, in from_params
    kwargs = create_kwargs(constructor_to_inspect, cls, params, **extras)
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 200, in create_kwargs
    cls.__name__, param_name, annotation, param.default, params, **extras
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 307, in pop_and_construct_arg
    return construct_arg(class_name, name, popped_params, annotation, default, **extras)
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 391, in construct_arg
    **extras,
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 341, in construct_arg
    return annotation.from_params(params=popped_params, **subextras)
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 604, in from_params
    **extras,
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 634, in from_params
    return constructor_to_call(**kwargs)  # type: ignore
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\modules\token_embedders\pretrained_transformer_mismatched_embedder.py", line 65, in __init__
    transformer_kwargs=transformer_kwargs,
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\modules\token_embedders\pretrained_transformer_embedder.py", line 105, in __init__
    tokenizer_kwargs=tokenizer_kwargs,
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\data\tokenizers\pretrained_transformer_tokenizer.py", line 71, in __init__
    model_name, add_special_tokens=False, **tokenizer_kwargs
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\cached_transformers.py", line 110, in get_tokenizer
    **kwargs,
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\transformers\models\auto\tokenization_auto.py", line 395, in from_pretrained
    return tokenizer_class_fast.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\transformers\tokenization_utils_base.py", line 1750, in from_pretrained
    use_auth_token=use_auth_token,
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\transformers\file_utils.py", line 1087, in cached_path
    local_files_only=local_files_only,
  File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\transformers\file_utils.py", line 1268, in get_from_cache
    "Connection error, and we cannot find the requested files in the cached path."
ValueError: Connection error, and we cannot find the requested files in the cached path. Please try again or make sure your Internet connection is on.

So what do I do wrong? How to make it works correctly?

[Daisy-a-p]

Hello! Could anyone give any idea how to make it work?

[nramrakhiyani]

If it matters to you now (almost a year later), the thing we tried was to untar-gz the coref-spanbert-large-2021.03.10.tar.gz model file and manually change the config.json inside it. The change involves changing every occurrence of "spanbert-large-cased" to the local path where the spanbert-large-cased model is stored. The tar.gz file, obtained by compressing the other files along with the modified config.json file, and loading that in Predictor.from_path works.