gemma-dqg-new / tokenizer_config.json
cvzion's picture
Upload folder using huggingface_hub
171bcca verified
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<bos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"106": {
"content": "<start_of_turn>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"107": {
"content": "<end_of_turn>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<start_of_turn>",
"<end_of_turn>"
],
"bos_token": "<bos>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if message['from'] == 'human' %}{{ '<|user|>\n' + message['value'] + eos_token + '\n' }}{% elif message['from'] == 'assistant' %}{{ '<|assistant|>\n' + message['value'] + eos_token + '\n' }}{% else %}{{ '<|system|>\n' + message['value'] + eos_token + '\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<eos>",
"legacy": null,
"model_max_length": 8192,
"pad_token": "<pad>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "GemmaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}