GemSUra-2B-hcmut-dpo / tokenizer_config.json
ledong0110's picture
Upload tokenizer
20b47bb 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>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<start_of_turn>user\n' + content + '<end_of_turn>\n<start_of_turn>model\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<end_of_turn>\n' }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<eos>",
"legacy": null,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"split_special_tokens": false,
"tokenizer_class": "GemmaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}