46 lines
1.2 KiB
JSON
46 lines
1.2 KiB
JSON
|
{
|
||
|
|
"add_bos_token": false,
|
||
|
|
"add_eos_token": false,
|
||
|
|
"added_tokens_decoder": {
|
||
|
|
"0": {
|
||
|
|
"content": "<unk>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"1": {
|
||
|
|
"content": "<s>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"2": {
|
||
|
|
"content": "</s>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"auto_map": {
|
||
|
|
"AutoTokenizer": [
|
||
|
|
"tokenization_orion.OrionTokenizer",
|
||
|
|
null
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"bos_token": "<s>",
|
||
|
|
"chat_template": "{% for message in messages %}{% if loop.first %}{{ bos_token }}{% endif %}{% if message['role'] == 'user' %}{{ 'Human: ' + message['content'] + '\n\nAssistant: ' + eos_token }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"eos_token": "</s>",
|
||
|
|
"model_max_length": 4096,
|
||
|
|
"pad_token": "<unk>",
|
||
|
|
"sp_model_kwargs": {},
|
||
|
|
"tokenizer_class": "OrionTokenizer",
|
||
|
|
"unk_token": "<unk>"
|
||
|
|
}
|