95 lines
2.3 KiB
JSON
95 lines
2.3 KiB
JSON
{
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "<sos>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"1": {
|
|
"content": "<pad>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"2": {
|
|
"content": "<|endoftext|>",
|
|
"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": "<|instruction|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"8": {
|
|
"content": "<|response|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"9": {
|
|
"content": "<|separator|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"bos_token": "<sos>",
|
|
"chat_template": "\n{%- for message in messages %}\n {%- if message['role'] == 'user' %}\n {{- '<|instruction|>' + ' ' + message['content'].strip() }}\n {%- elif message['role'] == 'assistant' %}\n {{- '<|response|>' + ' ' + message['content'].strip() }}\n {%- endif %}\n{%- endfor %}\n",
|
|
"clean_up_tokenization_spaces": true,
|
|
"eos_token": "<|endoftext|>",
|
|
"extra_special_tokens": {},
|
|
"model_max_length": 1000000000000000019884624838656,
|
|
"pad_token": "<pad>",
|
|
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
"trim_offsets": true,
|
|
"unk_token": "<unk>"
|
|
}
|