94 lines
2.4 KiB
JSON
94 lines
2.4 KiB
JSON
|
{
|
||
|
|
"added_tokens_decoder": {
|
||
|
|
"0": {
|
||
|
|
"content": "<|pad|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"1": {
|
||
|
|
"content": "<|bos|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"2": {
|
||
|
|
"content": "<|eos|>",
|
||
|
|
"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
|
||
|
|
},
|
||
|
|
"4": {
|
||
|
|
"content": "<|system|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"5": {
|
||
|
|
"content": "<|user|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"6": {
|
||
|
|
"content": "<|assistant|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"7": {
|
||
|
|
"content": "<|sep|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"8": {
|
||
|
|
"content": "<|endoftext|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"additional_special_tokens": [
|
||
|
|
"<|system|>",
|
||
|
|
"<|user|>",
|
||
|
|
"<|assistant|>",
|
||
|
|
"<|sep|>",
|
||
|
|
"<|endoftext|>"
|
||
|
|
],
|
||
|
|
"bos_token": "<|bos|>",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"eos_token": "<|eos|>",
|
||
|
|
"extra_special_tokens": {},
|
||
|
|
"model_max_length": 1000000000000000019884624838656,
|
||
|
|
"pad_token": "<|pad|>",
|
||
|
|
"tokenizer_class": "PreTrainedTokenizerFast",
|
||
|
|
"unk_token": "<|unk|>",
|
||
|
|
"add_bos_token": false,
|
||
|
|
"add_eos_token": false,
|
||
|
|
"chat_template": "{%- for message in messages -%}{%- if message['role'] == 'system' -%}<|system|> {{ message['content'] }}<|sep|>{%- elif message['role'] == 'user' -%}<|user|> {{ message['content'] }}<|sep|>{%- elif message['role'] == 'assistant' -%}<|assistant|> {{ message['content'] }}<|eos|>{%- endif -%}{%- endfor -%}{% if add_generation_prompt %}<|assistant|> {% endif %}"
|
||
|
|
}
|