DACMini-IT / tokenizer_config.json
Mattimax's picture
Upload tokenizer_config.json
cefd2dd verified
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30000": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30001": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|system|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"extra_special_tokens": {},
"max_length": 512,
"model_max_length": 1000000000000000019884624838656,
"pad_to_multiple_of": null,
"pad_token": "<|pad|>",
"pad_token_type_id": 0,
"padding_side": "right",
"stride": 0,
"tokenizer_class": "GPT2Tokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<|endoftext|>",
"chat_template": "{% if messages[0]['role'] != 'system' %}<|system|>\nTi chiami DACMini, un modello di intelligenza artificiale creato da M.INC.{% endif %}\n{% for message in messages %}{% if message['role'] == 'user' %}<|user|>\n{{ message['content'] }}{% elif message['role'] == 'assistant' %}<|assistant|>\n{{ message['content'] }}{% endif %}{% endfor %}\n<|assistant|>"
}