TinyLlama-1.1B-2.5T-chat / tokenizer_config.json
AIGym's picture
Upload tokenizer
ab2444f
raw
history blame
1.68 kB
{
"add_bos_token": true,
"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
}
},
"bos_token": "<s>",
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{%- set ns = namespace(found=false) -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{%- set ns.found = true -%}{%- endif -%}{%- endfor -%}{{bos_token}}{%- if not ns.found -%}{{'You are an AI assistant and you do your best to answer all questions and requests\n'}}{%- endif %}{%- for message in messages %}{%- if message['role'] == 'system' %}{{ message['content'] }}{%- else %}{%- if message['role'] == 'user' %}{{'Instruction:' + message['content'] + '\n'}}{%- else %}{{'\nOutput:' + message['content'] + '\n<|EOT|>\n'}}{%- endif %}{%- endif %}{%- endfor %}{% if add_generation_prompt %}{{'\nOutput:'}}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<unk>",
"padding_side": "left",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}