BERT

1.vocab

PRETRAINED_VOCAB_ARCHIVE_MAP = {
‘bert-base-uncased’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt”,
‘bert-large-uncased’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt”,
‘bert-base-cased’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-vocab.txt”,
‘bert-large-cased’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-vocab.txt”,
‘bert-base-multilingual-uncased’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-vocab.txt”,
‘bert-base-multilingual-cased’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased-vocab.txt”,
‘bert-base-chinese’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese-vocab.txt”
}

2.model_bin

PRETRAINED_MODEL_ARCHIVE_MAP = {
‘bert-base-uncased’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased.tar.gz”,
‘bert-large-uncased’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased.tar.gz”,
‘bert-base-cased’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased.tar.gz”,
‘bert-large-cased’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased.tar.gz”,
‘bert-base-multilingual-uncased’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased.tar.gz”,
‘bert-base-multilingual-cased’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased.tar.gz”,
‘bert-base-chinese’: “https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese.tar.gz”
}

RoBERTa

1.config

ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = {
"roberta-base": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-config.json",
"roberta-large": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-config.json",
"roberta-large-mnli": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-config.json",
"distilroberta-base": "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-config.json",
"roberta-base-openai-detector": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-openai-detector-config.json",
"roberta-large-openai-detector": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-openai-detector-config.json",
}

2.vocab

PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {
"roberta-base": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-vocab.json",
"roberta-large": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-vocab.json",
"roberta-large-mnli": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-vocab.json",
"distilroberta-base": "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-vocab.json",
"roberta-base-openai-detector": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-vocab.json",
"roberta-large-openai-detector": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-vocab.json",
},
"merges_file": {
"roberta-base": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-merges.txt",
"roberta-large": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-merges.txt",
"roberta-large-mnli": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-merges.txt",
"distilroberta-base": "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-merges.txt",
"roberta-base-openai-detector": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-merges.txt",
"roberta-large-openai-detector": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-merges.txt",
},
}

3.model_bin

ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP = {
"roberta-base": "https://cdn.huggingface.co/roberta-base-pytorch_model.bin",
"roberta-large": "https://cdn.huggingface.co/roberta-large-pytorch_model.bin",
"roberta-large-mnli": "https://cdn.huggingface.co/roberta-large-mnli-pytorch_model.bin",
"distilroberta-base": "https://cdn.huggingface.co/distilroberta-base-pytorch_model.bin",
"roberta-base-openai-detector": "https://cdn.huggingface.co/roberta-base-openai-detector-pytorch_model.bin",
"roberta-large-openai-detector": "https://cdn.huggingface.co/roberta-large-openai-detector-pytorch_model.bin",
}

参考：

https://www.kaggle.com/c/tweet-sentiment-extraction/discussion/150007
https://blog.csdn.net/weixin_44287209/article/details/108792846