naija-xlm-twitter-base-hate / tokenizer_config.json
manueltonneau's picture
Upload 11 files
1dd5748 verified
raw
history blame contribute delete
705 Bytes
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"do_lower_case": false,
"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": "/scratch/spf248/twitter_social_cohesion/models/pretrained/xlmr/5e-5_42_ddp/checkpoint-final",
"pad_token": "<pad>",
"sep_token": "</s>",
"special_tokens_map_file": "/scratch/spf248/twitter_social_cohesion/models/pretrained/xlmr/5e-5_42_ddp/checkpoint-final/special_tokens_map.json",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}