dakshvar22's picture
Upload tokenizer
7633867 verified
{
"add_bos_token": true,
"add_eos_token": 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
},
"32007": {
"content": "▁<PRE>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32008": {
"content": "▁<SUF>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32009": {
"content": "▁<MID>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32010": {
"content": "▁<EOT>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"▁<PRE>",
"▁<MID>",
"▁<SUF>",
"▁<EOT>"
],
"bos_token": "<s>",
"chat_template": "{% if 'role' in messages[0] %}{% if messages[0]['role'] == 'system' %}{% if messages[1]['role'] == 'user' %}{{ bos_token + '[INST] <<SYS>>\n' + messages[0]['content'] + '\n<</SYS>>\n\n' + messages[1]['content'] + ' [/INST]' }}{% set loop_messages = messages[2:] %}{% else %}{{ bos_token + '[INST] ' + messages[0]['content'] + ' [/INST]' }}{% set loop_messages = messages[1:] %}{% endif %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + message['content'].strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'].strip() + ' ' + eos_token }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% else %}{% if messages[0]['from'] == 'system' %}{% if messages[1]['from'] == 'human' %}{{ bos_token + '[INST] <<SYS>>\n' + messages[0]['value'] + '\n<</SYS>>\n\n' + messages[1]['value'] + ' [/INST]' }}{% set loop_messages = messages[2:] %}{% else %}{{ bos_token + '[INST] ' + messages[0]['value'] + ' [/INST]' }}{% set loop_messages = messages[1:] %}{% endif %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['from'] == 'human' %}{{ bos_token + '[INST] ' + message['value'].strip() + ' [/INST]' }}{% elif message['from'] == 'gpt' %}{{ ' ' + message['value'].strip() + ' ' + eos_token }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"eot_token": "▁<EOT>",
"fill_token": "<FILL_ME>",
"legacy": null,
"middle_token": "▁<MID>",
"model_max_length": 16384,
"pad_token": "<unk>",
"padding_side": "left",
"prefix_token": "▁<PRE>",
"sp_model_kwargs": {},
"suffix_token": "▁<SUF>",
"tokenizer_class": "CodeLlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}