h2o-danube3.1-4b-chat / tokenizer_config.json
gaborfodorh2o's picture
Upload folder using huggingface_hub
e649b5c verified
{
"add_bos_token": false,
"add_eos_token": false,
"add_prefix_space": 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
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{% for message in messages %}{% if loop.index0 != 0 and message['role'] == 'system' %}{{ raise_exception('Conversation roles must alternate system(optional)/user/assistant/user/assistant/...') }}{% elif messages[0]['role'] == 'system' and ((message['role'] == 'user' and (loop.index0 % 2 == 0)) or (message['role'] == 'assistant' and (loop.index0 % 2 == 1))) %}{{ raise_exception('Conversation roles must alternate system(optional)/user/assistant/user/assistant/...') }}{% elif messages[0]['role'] != 'system' and ((message['role'] == 'user' and (loop.index0 % 2 != 0)) or (message['role'] == 'assistant' and (loop.index0 % 2 != 1))) %}{{ raise_exception('Conversation roles must alternate system(optional)/user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '<|prompt|>' + message['content'].strip() + eos_token }}{% elif message['role'] == 'system' %}{{ '<|system|>' + message['content'].strip() + eos_token }}{% elif message['role'] == 'assistant' %}{{ '<|answer|>' + message['content'].strip() + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|answer|>' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"cls_token": "</s>",
"eos_token": "</s>",
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<unk>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}