OpenELM-3B-SFT-D1_chosen-then-D2_chosen-HuggingFaceH4-ultrafeedback_binarized-Xlarge
/
tokenizer_config.json
{ | |
"add_bos_token": true, | |
"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 | |
} | |
}, | |
"bos_token": "<s>", | |
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif USE_DEFAULT_PROMPT == true and not '<<SYS>>' in messages[0]['content'] %}{% set loop_messages = messages %}{% set system_message = 'DEFAULT_SYSTEM_MESSAGE' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if loop_messages|length == 0 and system_message %}{{ bos_token + '[INST] <<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n [/INST]' }}{% endif %}{% for message in loop_messages %}{% 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'] == 'system' %}{{ '<<SYS>>\\n' + content.strip() + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}", | |
"clean_up_tokenization_spaces": false, | |
"eos_token": "</s>", | |
"legacy": false, | |
"model_max_length": 1000000000000000019884624838656, | |
"pad_token": "</s>", | |
"padding_side": "right", | |
"sp_model_kwargs": {}, | |
"tokenizer_class": "LlamaTokenizer", | |
"unk_token": "<unk>", | |
"use_default_system_prompt": false | |
} | |