| { | |
| "add_prefix_space": true, | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<s>", | |
| "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": "<pad>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "4": { | |
| "content": "<sep>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "5": { | |
| "content": "<mask>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "6": { | |
| "content": "<cls>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "51200": { | |
| "content": "<|system|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "51201": { | |
| "content": "<|assistant|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "51202": { | |
| "content": "<|user|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": [ | |
| "<|system|>", | |
| "<|assistant|>", | |
| "<|user|>" | |
| ], | |
| "bos_token": "<s>", | |
| "chat_template": "{%- for message in messages -%}\n{%- if message['role'] == 'assistant' -%}\n{{ '<|assistant|>' + message['content'] + eos_token }}\n{%- elif message['role'] == 'system' -%}\n{{ '<|system|>' + message['content'] + eos_token }}\n{%- elif message['role'] == 'user' -%}\n{{ '<|user|>' + message['content'] + eos_token }}\n{%- endif -%}\n{%- if loop.last and add_generation_prompt -%}\n{{ '<|assistant|>' }}\n{%- endif -%}\n{%- endfor -%}", | |
| "clean_up_tokenization_spaces": true, | |
| "cls_token": "<cls>", | |
| "do_lower_case": false, | |
| "eos_token": "</s>", | |
| "extra_ids": 0, | |
| "keep_accents": true, | |
| "legacy": true, | |
| "mask_token": "<mask>", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<pad>", | |
| "padding_side": "right", | |
| "sep_token": "<sep>", | |
| "sp_model_kwargs": {}, | |
| "tokenizer_class": "T5Tokenizer", | |
| "unk_token": "<unk>" | |
| } | |