Tess-7B-v2.0 / tokenizer_config.json
Handgun1773's picture
Update tokenizer config with inspiration from eric's dolphin.
5d643fe verified
raw
history blame
1.51 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
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{% if message['role'] == 'system' %}{{ 'SYSTEM: ' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ 'USER: ' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{{ 'ASSISTANT: ' + message['content'] + '\n' }}{% else %}{{ raise_exception('Unsupported role: ' + message['role']) }}{% endif %}{% endfor %}{% if add_generation_prompt %}ASSISTANT: {% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}