T-VisStar-7B-v0.1 / tokenizer_config.json
1TuanPham's picture
Upload tokenizer
19fcaf8 verified
raw
history blame
3.16 kB
{
"add_bos_token": false,
"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
},
"38365": {
"content": "[SYSMSG]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"38366": {
"content": "[/SYSMSG]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"38367": {
"content": "[USER]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"38368": {
"content": "[/USER]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"38369": {
"content": "[/Assistant]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"38370": {
"content": "[Assistant]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"38371": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>",
"[PAD]"
],
"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 = false %}{% endif %}{{ bos_token }}{% if system_message != false %}[SYSMSG] {{ system_message | trim }} [/SYSMSG] \n\n{% 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 message['role'] == 'user' %}{% if loop.index0 != 0 %}{{bos_token}} {% endif %}[USER] {{ message['content'] | trim }} [/USER] {% elif message['role'] == 'assistant' %}[Assistant] {{ message['content'] | trim }} [/Assistant] {{ eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}[Assistant] {% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 32768,
"pad_token": "[PAD]",
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false,
"use_fast": true
}