| { | |
| "add_bos_token": false, | |
| "add_eos_token": false, | |
| "add_prefix_space": null, | |
| "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 | |
| } | |
| }, | |
| "additional_special_tokens": [], | |
| "bos_token": "<s>", | |
| "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% set messages = messages[1:] %}{% else %}{% set system_message = 'SYSTEM:你是由Mistral AI所開發、經台灣詞庫小組(CKIP)後續優化的語言模型，優化目標為提升台灣正體中文任務的表現與在地化，主要的使用者來自於台灣。\n\n' %}{% endif %}{{system_message}}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate system/user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ 'Human:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant:\n' + message['content'] + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:\n' }}{% endif %}", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "</s>", | |
| "legacy": true, | |
| "model_max_length": 4096, | |
| "pad_token": "</s>", | |
| "padding_side": "left", | |
| "sp_model_kwargs": {}, | |
| "spaces_between_special_tokens": false, | |
| "tokenizer_class": "LlamaTokenizer", | |
| "truncation_side": "left", | |
| "unk_token": "<unk>", | |
| "use_default_system_prompt": false | |
| } | |