politweets-new / tokenizer_config.json
Andrej
added model and tokenizer
9aa46e1
raw
history blame contribute delete
742 Bytes
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"name_or_path": "manifesto-project/manifestoberta-xlm-roberta-56policy-topics-sentence-2023-1-1",
"pad_token": "<pad>",
"sep_token": "</s>",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--manifesto-project--manifestoberta-xlm-roberta-56policy-topics-sentence-2023-1-1/snapshots/f84c5fe28cd5638eaae863f293710e2988d9ad10/special_tokens_map.json",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}