robertuito-sentiment-analysis / tokenizer_config.json
Xenova's picture
Xenova HF staff
Upload folder using huggingface_hub
f6a0b34 verified
{
"added_tokens_decoder": {
"0": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"430": {
"content": "@usuario",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"27394": {
"content": "url",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"30000": {
"content": "hashtag",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"30001": {
"content": "emoji",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": "<mask>",
"max_length": 128,
"model_max_length": 128,
"pad_token": "<pad>",
"sep_token": "</s>",
"stride": 0,
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>"
}