malaysian-tinyllama-multimodal / tokenizer_config.json
aisyahhrazak's picture
Upload tokenizer
e564d99 verified
raw
history blame
2.56 kB
{
"add_bos_token": false,
"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
},
"32000": {
"content": "<image>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32001": {
"content": "</image>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32002": {
"content": "<audio>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32003": {
"content": "</audio>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in 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 message['content'] is not none and message['content'].strip() != '' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% endif %}{% elif message['role'] == 'assistant' %}{% if messages[loop.index0 - 1]['content'] is not none and messages[loop.index0 - 1]['content'].strip() != '' and message['content'] is not none and message['content'].strip() != '' %}{{ message['content'] + eos_token }}{% endif %}{% else %}{{ print('Unexpected role encountered:', message['role']) }}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"max_length": 8192,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<unk>",
"padding_side": "right",
"sp_model_kwargs": {},
"stride": 0,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>",
"use_default_system_prompt": false
}