lsg-camembert-base-4096 / tokenizer_config.json
ccdv's picture
readme
a6e4b5a
raw
history blame contribute delete
456 Bytes
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"], "model_max_length": 4096, "special_tokens_map_file": null, "name_or_path": "camembert-base", "tokenizer_class": "CamembertTokenizer"}