SQL_Sorcerer_2.7B_V1.0 / tokenizer_config.json
MrezaPRZ's picture
Upload tokenizer
0c34847
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50257": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50258": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50259": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50260": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50261": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50262": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50263": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50264": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50265": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50266": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50267": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50268": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50269": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50270": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50271": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50272": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50273": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50274": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50275": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50276": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50277": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50278": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50279": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50280": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50281": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50282": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50283": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50284": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50285": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50286": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50287": {
"content": "\t\t\t\t\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50288": {
"content": "\t\t\t\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50289": {
"content": "\t\t\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50290": {
"content": "\t\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50291": {
"content": "\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50292": {
"content": "\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50293": {
"content": "\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50294": {
"content": "\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<|endoftext|>",
"chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 2048,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CodeGenTokenizer",
"unk_token": "<|endoftext|>"
}