bart_wikikp_ftuned_cve50k / tokenizer_config.json
ahadda5's picture
add tokenizer
c3d362d
raw
history blame
No virus
1.66 kB
{
"add_prefix_space": false,
"additional_special_tokens": [
"<present>",
"<absent>",
"<category>",
"<infill>",
"<seealso>",
"<header>",
"<|endoftext|>",
"<sep>",
"<mask>",
"<mixed>",
"<number>",
"<phrase>"
],
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"name_or_path": "memray/bart_wikikp",
"pad_token": {
"__type": "AddedToken",
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sep": "<sep>",
"sep_token": "<sep>",
"special_tokens_map_file": "/home/ashraf.haddad/.cache/huggingface/transformers/4b7a3619321a39f6780e0c775802e3523e52c1efd3a46e6d1baac9e1e8e234e6.898eb95aac9bb57440c2f57caa963ae18b9b10ba4731cc81020283286b0391fc",
"tokenizer_class": "BartTokenizer",
"trim_offsets": true,
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}