9

I`m beginner.. I'm working with Bert. However, due to the security of the company network, the following code does not receive the bert model directly.

tokenizer = BertTokenizer.from_pretrained('bert-base-multilingual-cased', do_lower_case=False)
model = BertForSequenceClassification.from_pretrained("bert-base-multilingual-cased", num_labels=2)

So I think I have to download these files and enter the location manually. But I'm new to this, and I'm wondering if it's simple to download a format like .py from github and put it in a location.

I'm currently using the bert model implemented by hugging face's pytorch, and the address of the source file I found is:

https://github.com/huggingface/transformers

Please let me know if the method I thought is correct, and if so, what file to get.

Thanks in advance for the comment.

Improve this question

1 Answer 1

Reset to default
14

As described here, what you need to do are download pre_train and configs, then putting them in the same folder. Every model has a pair of links, you might want to take a look at lib code.

For instance

import torch
from transformers import *
model = BertModel.from_pretrained('/Users/yourname/workplace/berts/')

with /Users/yourname/workplace/berts/ refer to your folder

Below are what I found

at src/transformers/configuration_bert.py there are a list of models' configs

BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "bert-base-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-config.json",
    "bert-large-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-config.json",
    "bert-base-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-config.json",
    "bert-large-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-config.json",
    "bert-base-multilingual-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-config.json",
    "bert-base-multilingual-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased-config.json",
    "bert-base-chinese": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese-config.json",
    "bert-base-german-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-cased-config.json",
    "bert-large-uncased-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-config.json",
    "bert-large-cased-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-config.json",
    "bert-large-uncased-whole-word-masking-finetuned-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-finetuned-squad-config.json",
    "bert-large-cased-whole-word-masking-finetuned-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-finetuned-squad-config.json",
    "bert-base-cased-finetuned-mrpc": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-config.json",
    "bert-base-german-dbmdz-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-config.json",
    "bert-base-german-dbmdz-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-config.json",
    "bert-base-japanese": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-config.json",
    "bert-base-japanese-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-whole-word-masking-config.json",
    "bert-base-japanese-char": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-config.json",
    "bert-base-japanese-char-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-whole-word-masking-config.json",
    "bert-base-finnish-cased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-cased-v1/config.json",
    "bert-base-finnish-uncased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-uncased-v1/config.json",
}

and at src/transformers/modeling_bert.py there are links to pre_trains

BERT_PRETRAINED_MODEL_ARCHIVE_MAP = {
    "bert-base-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-pytorch_model.bin",
    "bert-large-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-pytorch_model.bin",
    "bert-base-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-pytorch_model.bin",
    "bert-large-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-pytorch_model.bin",
    "bert-base-multilingual-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-pytorch_model.bin",
    "bert-base-multilingual-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased-pytorch_model.bin",
    "bert-base-chinese": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese-pytorch_model.bin",
    "bert-base-german-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-cased-pytorch_model.bin",
    "bert-large-uncased-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-pytorch_model.bin",
    "bert-large-cased-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-pytorch_model.bin",
    "bert-large-uncased-whole-word-masking-finetuned-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-finetuned-squad-pytorch_model.bin",
    "bert-large-cased-whole-word-masking-finetuned-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-finetuned-squad-pytorch_model.bin",
    "bert-base-cased-finetuned-mrpc": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-pytorch_model.bin",
    "bert-base-german-dbmdz-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-pytorch_model.bin",
    "bert-base-german-dbmdz-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-pytorch_model.bin",
    "bert-base-japanese": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-pytorch_model.bin",
    "bert-base-japanese-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-whole-word-masking-pytorch_model.bin",
    "bert-base-japanese-char": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-pytorch_model.bin",
    "bert-base-japanese-char-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-whole-word-masking-pytorch_model.bin",
    "bert-base-finnish-cased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-cased-v1/pytorch_model.bin",
    "bert-base-finnish-uncased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-uncased-v1/pytorch_model.bin",
}
Improve this answer
9
  • Thank you very much for the first reply! I've seen that issue when I load the model 1. save them in a directory and rename them respectively config.json and pytorch_model.bin 2. `model = BertModel.from_pretrained('path/to/your/directory')' I used the method of "I downloaded the model of bert-base-multilingual-cased above and it says undefined name."
    – ybin
    Jan 12, 2020 at 13:36
  • 1
    after downloading, and moving to your company's folder, during running time, do you have any difficulty?
    – Bryan
    Jan 12, 2020 at 13:39
  • I put the file in the same directory as the file in my jupyter notebook and ran it as follows: 'model = BertModel.from_pretrained ('./')' Can you tell me some examples of code use?
    – ybin
    Jan 12, 2020 at 13:39
  • 1
    I see. I added more details, can u check it. I guessed the reason was Bert-base-multilingual-case, there is no class has this name
    – Bryan
    Jan 12, 2020 at 13:52
  • 1
    depending on what you want. In transformers, the lib provides transforms and fine-tuning on down-stream tasks. These classes are BertModel, BertForPreTraining, BertForMaskedLM, BertForNextSentencePrediction, BertForSequenceClassification, BertForTokenClassification, BertForQuestionAnswering
    – Bryan
    Jan 12, 2020 at 14:05

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.