kaggle-llm-prompt-recovery-from-gemma / tokenizer_config.json
fhatje's picture
Upload tokenizer
df0af9e verified
raw
history blame
No virus
1.64 kB
{
"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
}
},
"bos_token": "<bos>",
"chat_template": "{%for message in messages%}{%if message['type']=='instruction'%}{{bos_token+'[INST]'+message['content']+'[/INST]'}}{%elif message['type']=='original'%}{{'<<ORIG>>\\n'+message['content']+'\\n<</ORIG>>\\n'}}{%elif message['type']=='revised'%}{{'<<REV>>\\n'+message['content']+'\\n<</REV>>\\n'}}{%elif message['type']=='prompt'%}{%if not add_generation_prompt%}{{'<<PRMPT>>\\n'+message['content']+'\\n<</PRMPT>>'+eos_token}}{%endif%}{%endif%}{%endfor%}{%if add_generation_prompt%}{{'<<PRMPT>>\\n'}}{%endif%}",
"clean_up_tokenization_spaces": false,
"eos_token": "<eos>",
"legacy": null,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "GemmaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}