62 lines
1.6 KiB
JSON
62 lines
1.6 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": "<|startoftext|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"2": {
|
|
"content": "<|endoftext|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"6": {
|
|
"content": "<|im_start|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
},
|
|
"7": {
|
|
"content": "<|im_end|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": false
|
|
}
|
|
},
|
|
"auto_map": {
|
|
"AutoTokenizer": [
|
|
"tokenization_yi.YiTokenizer",
|
|
null
|
|
]
|
|
},
|
|
"bos_token": "<|startoftext|>",
|
|
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|im_end|>",
|
|
"model_max_length": 4096,
|
|
"pad_token": "<unk>",
|
|
"sp_model_kwargs": {},
|
|
"tokenizer_class": "YiTokenizer",
|
|
"unk_token": "<unk>"
|
|
}
|