Pangu_alpha / tokenizer_config.json
Hanlard's picture
Upload 6 files
afbba8e
raw
history blame
465 Bytes
{"do_lower_case": false, "remove_space": true, "keep_accents": false, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": [ "<eod>"], "special_tokens_map_file": null, "name_or_path": "TsinghuaAI/CPM-Generate", "tokenizer_class": "CpmTokenizer"}