CodeBertForCodeTrans / tokenizer_config.json
ljcnju's picture
Training in progress, epoch 1
4cb774f verified
raw
history blame
2.33 kB
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50264": {
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50265": {
"content": "<|begin_of_java_code|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50266": {
"content": "<|end_of_java_code|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50267": {
"content": "<|begin_of_c-sharp_code|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50268": {
"content": "<|end_of_c-sharp_code|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50269": {
"content": "<|translate|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|begin_of_java_code|>",
"<|end_of_java_code|>",
"<|begin_of_c-sharp_code|>",
"<|end_of_c-sharp_code|>",
"<|translate|>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": "<mask>",
"model_max_length": 512,
"pad_token": "</s>",
"sep_token": "</s>",
"tokenizer_class": "RobertaTokenizer",
"trim_offsets": true,
"unk_token": "<unk>"
}