tokenizer_uni_domain_16000 / tokenizer_config.json
rdxsun's picture
Create tokenizer_config.json
4ce9353
raw
history blame contribute delete
402 Bytes
{"src_lang": null, "tgt_lang": null, "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": "<s>", "tokenizer_file": null, "model_max_length": 1024, "special_tokens_map_file": "special_tokens_map.json"}