paulo037's picture
Upload tokenizer
cf23e02 verified
{
"add_bos_token": true,
"add_eos_token": 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": true,
"single_word": false,
"special": false
},
"32000": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32002": {
"content": "<|placeholder1|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32003": {
"content": "<|placeholder2|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32004": {
"content": "<|placeholder3|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32005": {
"content": "<|placeholder4|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32006": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32007": {
"content": "<|end|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32008": {
"content": "<|placeholder5|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32009": {
"content": "<|placeholder6|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32010": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32011": {
"content": "[SQL]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32012": {
"content": "[/SQL]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32013": {
"content": "[INFO]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32014": {
"content": "[/INFO]",
"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'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are an SQL expert tasked with answering questions about an SQLite database.\nYour responses must always consist of valid SQL code and only that.' %}{% endif %}{{ '# <|system|>\n' + system_message + '\n\n' }}{% if messages|selectattr(\"role\", \"equalto\", \"example\")|list %}Below are some examples of question and their corresponding SQL queries:\n\n{% else %}\n{% endif %}{% for message in loop_messages %}{% if message['role'] == 'example' %}{{ message['content'] }}{% elif message['role'] == 'schema' %}\nThe query will run on a database with the following schema:\n{{ message['content'] }}<|end|>{% elif message['role'] == 'user' %}<|user|>\n{{ message['content'] }}<|end|>{% elif message['role'] == 'sqlite' %}<|sqlite|>\n{{ message['content']}}<|end|>{% elif message['role'] == 'assistant' %}<|assistant|>\n{{ message['content']}}<|end|>{% endif %}{% if loop_messages[-1] != message %} \n\n{% endif %}{% endfor %}{% if add_generation_prompt %}\n\n\n<|assistant|>\n{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"legacy": false,
"map_device": "auto",
"model_max_length": 131072,
"pad_token": "<unk>",
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}