Llammas-base-p1-llama-errors-p2-GEC / tokenizer_config.json
taidopurason's picture
Upload tokenizer
e3bfcd4 verified
raw
history blame
1.39 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": "{% for message in messages %}{% if (message['role'] == 'user') and (loop.index0 == 0) %}{{ '### Instruction:\nReply with a corrected version of the input sentence in Estonian with all grammatical and spelling errors fixed. If there are no errors, reply with a copy of the original sentence.\n\n### Input:\n' + message['content'] + '\n\n### Response:\n' }}{% else %}{{ raise_exception('Only single user input turn allowed.') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}