| { | |
| "add_bos_token": true, | |
| "add_eos_token": false, | |
| "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": "<MASK|LLM-jp>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "4": { | |
| "content": "<PAD|LLM-jp>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "5": { | |
| "content": "<CLS|LLM-jp>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "6": { | |
| "content": "<SEP|LLM-jp>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "7": { | |
| "content": "<EOD|LLM-jp>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "bos_token": "<s>", | |
| "chat_template": "{% if 'role' in messages[0] %}{{ bos_token }}{% if 'role' in messages[0] %}{% if messages[0]['role'] == 'system' %}{{ messages[0]['content'] + '\n\n' }}{% set loop_messages = messages[1:] %}{% else %}{{ '以下に、いくつかのタスクについて説明します。各リクエストを適切に完了する応答を記述してください。' + '\n\n' }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '### 指示:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### 回答:\n' + message['content'] + eos_token + '\n\n' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### Response:\n' }}{% endif %}{% else %}{% if messages[0]['from'] == 'system' %}{{ messages[0]['value'] + '\n\n' }}{% set loop_messages = messages[1:] %}{% else %}{{ '以下に、いくつかのタスクについて説明します。各リクエストを適切に完了する応答を記述してください。' + '\n\n' }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['from'] == 'human' %}{{ '### 指示:\n' + message['value'] + '\n\n' }}{% elif message['from'] == 'gpt' %}{{ '### 回答:\n' + message['value'] + eos_token + '\n\n' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### 回答:\n' }}{% endif %}{% endif %}{% else %}{{ bos_token }}{% if 'from' in messages[0] %}{% if messages[0]['from'] == 'system' %}{{ messages[0]['value'] + '\n\n' }}{% set loop_messages = messages[1:] %}{% else %}{{ '以下に、いくつかのタスクについて説明します。各リクエストを適切に完了する応答を記述してください。' + '\n\n' }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['from'] == 'human' %}{{ '### 指示:\n' + message['value'] + '\n\n' }}{% elif message['from'] == 'gpt' %}{{ '### 回答:\n' + message['value'] + eos_token + '\n\n' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### Response:\n' }}{% endif %}{% else %}{% if messages[0]['from'] == 'system' %}{{ messages[0]['value'] + '\n\n' }}{% set loop_messages = messages[1:] %}{% else %}{{ '以下に、いくつかのタスクについて説明します。各リクエストを適切に完了する応答を記述してください。' + '\n\n' }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['from'] == 'human' %}{{ '### 指示:\n' + message['value'] + '\n\n' }}{% elif message['from'] == 'gpt' %}{{ '### 回答:\n' + message['value'] + eos_token + '\n\n' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### 回答:\n' }}{% endif %}{% endif %}{% endif %}", | |
| "clean_up_tokenization_spaces": false, | |
| "cls_token": "<CLS|LLM-jp>", | |
| "eod_token": "</s>", | |
| "eos_token": "</s>", | |
| "extra_ids": 0, | |
| "extra_special_tokens": {}, | |
| "mask_token": "<MASK|LLM-jp>", | |
| "max_length": 1024, | |
| "model_max_length": 4096, | |
| "pad_to_multiple_of": null, | |
| "pad_token": "<PAD|LLM-jp>", | |
| "pad_token_type_id": 0, | |
| "padding_side": "left", | |
| "sep_token": "<SEP|LLM-jp>", | |
| "sp_model_kwargs": {}, | |
| "stride": 0, | |
| "tokenizer_class": "PreTrainedTokenizer", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "<unk>" | |
| } | |