llm-jp-13b-instruct-full-ac_001-dolly-ichikara_004_001_single-oasst-oasst2-v2.0
/
tokenizer_config.json
| { | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<unk|LLM-jp>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<s|LLM-jp>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "</s|LLM-jp>", | |
| "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 | |
| } | |
| }, | |
| "additional_special_tokens": [ | |
| "</s|LLM-jp>" | |
| ], | |
| "bos_token": "<s|LLM-jp>", | |
| "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '\\n\\n### 指示:\\n' + message['content'] }}{% elif message['role'] == 'system' %}{{ '以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。' }}{% elif message['role'] == 'assistant' %}{{ '\\n\\n### 応答:\\n' + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '\\n\\n### 応答:\\n' }}{% endif %}{% endfor %}", | |
| "clean_up_tokenization_spaces": false, | |
| "cls_token": "<CLS|LLM-jp>", | |
| "eod_token": "<EOD|LLM-jp>", | |
| "eos_token": "<EOD|LLM-jp>", | |
| "extra_ids": 0, | |
| "mask_token": "<mask|LLM-jp>", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<pad|LLM-jp>", | |
| "sep_token": "<SEP|LLM-jp>", | |
| "sp_model_kwargs": {}, | |
| "tokenizer_class": "PreTrainedTokenizerFast", | |
| "unk_token": "<unk|LLM-jp>" | |
| } | |