JAIS_13b_anti_CF / tokenizer_config.json
ElmehdiSMILI's picture
Upload tokenizer
54f735f verified
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": 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": false,
"single_word": false,
"special": true
},
"64000": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64001": {
"content": "[|instruct_pointer|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64002": {
"content": "[|context_pointer|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64003": {
"content": "[|subject_pointer|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64004": {
"content": "[|response_pointer|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64005": {
"content": " [|Number_of_sub_instructions|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64006": {
"content": "[|/Number_of_sub_instructions|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64007": {
"content": "[|List_of_contexts|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64008": {
"content": "[|/List_of_contexts|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64009": {
"content": "[|context_delimiter|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64010": {
"content": "[\\|context_delimiter|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64011": {
"content": "[|sub_instruct|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64012": {
"content": "[|context_specifier|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64013": {
"content": "[/|context_specifier|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64014": {
"content": "<|information_retrieval_variant_1|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64015": {
"content": "[|input_specifier|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64016": {
"content": "[/|input_specifier|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64017": {
"content": "[/|sub_instruct|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64018": {
"content": "[|chat_information_placeholder|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64019": {
"content": "[/|chat_information_placeholder|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64020": {
"content": "<|classification_variant_1|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64021": {
"content": "<|summary_variant_1|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64022": {
"content": "[|input_*|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64023": {
"content": "[|input_name|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64024": {
"content": "[/|input_name|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64025": {
"content": "[/|input_*|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64026": {
"content": "[|response_*|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64027": {
"content": "[|response_number|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64028": {
"content": "[/|response_number|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64029": {
"content": "[/|response_*|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64030": {
"content": "[|STOP|]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"[|instruct_pointer|]",
"[|context_pointer|]",
"[|subject_pointer|]",
"[|response_pointer|]",
" [|Number_of_sub_instructions|]",
"[|/Number_of_sub_instructions|]",
"[|List_of_contexts|]",
"[|/List_of_contexts|]",
"[|context_delimiter|]",
"[\\|context_delimiter|]",
"[|sub_instruct|]",
"[|context_specifier|]",
"[/|context_specifier|]",
"<|information_retrieval_variant_1|>",
"[|input_specifier|]",
"[/|input_specifier|]",
"[/|sub_instruct|]",
"[|chat_information_placeholder|]",
"[/|chat_information_placeholder|]",
"<|classification_variant_1|>",
"<|summary_variant_1|>",
"[|input_*|]",
"[|input_name|]",
"[/|input_name|]",
"[/|input_*|]",
"[|response_*|]",
"[|response_number|]",
"[/|response_number|]",
"[/|response_*|]",
"[|STOP|]"
],
"bos_token": "<s>",
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = '### Instruction: ' + messages[0]['content'] + '\nComplete the conversation below between [|Human|] and [|AI|]:\n### Input:'%}{% else %}{% set loop_messages = messages %}{% set system_message = '### Instruction: Your name is \\'Jais\\', and you are named after Jebel Jais, the highest mountain in UAE. You were made by \\'Inception\\' in the UAE. You are a helpful, respectful, and honest assistant. Always answer as helpfully as possible, while being safe. Complete the conversation below between [|Human|] and [|AI|]:\n### Input:' %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = system_message %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{% if loop.index0 == 0 %}{{ content + ' [|Human|] ' + message['content'] }}{% else %}{{ '\n[|Human|] ' + content.strip() }}{% endif %}{% elif message['role'] == 'assistant' %}{{ '\n[|AI|] ' + content.strip() }}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %} {{'\n[|AI|]\n### Response:'}}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|pad|>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}