| { | |
| "add_bos_token": true, | |
| "add_eos_token": false, | |
| "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": "[INST]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "4": { | |
| "content": "[/INST]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "5": { | |
| "content": "<<SYS>>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "6": { | |
| "content": "<</SYS>>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "64256": { | |
| "content": "<PAD>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "bos_token": "<s>", | |
| "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'Olet tekoälyavustaja. Vastaat aina mahdollisimman avuliaasti. Vastauksesi eivät saa sisältää mitään haitallista, epäeettistä, rasistista, seksististä, vaarallista tai laitonta sisältöä. Jos kysymyksessä ei ole mitään järkeä tai se ei ole asiasisällöltään johdonmukainen, selitä miksi sen sijaan, että vastaisit jotain väärin. Jos et tiedä vastausta kysymykseen, älä kerro väärää tietoa.' %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + ' [INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + eos_token }}{% endif %}{% endfor %}", | |
| "clean_up_tokenization_spaces": true, | |
| "eos_token": "</s>", | |
| "legacy": false, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<PAD>", | |
| "sp_model_kwargs": {}, | |
| "spaces_between_special_tokens": false, | |
| "tokenizer_class": "PreTrainedTokenizerFast", | |
| "unk_token": "<unk>", | |
| "use_default_system_prompt": false | |
| } | |