bart-large-cnn-samsum / tokenizer_config.json
AdamCodd's picture
Upload 8 files
0863237
raw
history blame
No virus
1.38 kB
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50264": {
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": "<mask>",
"model_max_length": 1024,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "BartTokenizer",
"tokenizer_file": "/root/.cache/huggingface/hub/models--facebook--bart-large-cnn/snapshots/deb0f97cf6acb4f0a691356ed00ea06bf7e86e8f/tokenizer.json",
"unk_token": "<unk>"
}