71 lines
1.8 KiB
JSON
71 lines
1.8 KiB
JSON
|
{
|
||
|
|
"add_bos_token": false,
|
||
|
|
"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": "<|im_start|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"107": {
|
||
|
|
"content": "<|im_end|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"additional_special_tokens": [
|
||
|
|
"<|im_start|>",
|
||
|
|
"<|im_end|>"
|
||
|
|
],
|
||
|
|
"bos_token": "<bos>",
|
||
|
|
"chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"eos_token": "<eos>",
|
||
|
|
"legacy": null,
|
||
|
|
"model_max_length": 2048,
|
||
|
|
"pad_token": "<pad>",
|
||
|
|
"sp_model_kwargs": {},
|
||
|
|
"spaces_between_special_tokens": false,
|
||
|
|
"tokenizer_class": "GemmaTokenizer",
|
||
|
|
"unk_token": "<unk>",
|
||
|
|
"use_default_system_prompt": false
|
||
|
|
}
|