70 lines
1.6 KiB
JSON
70 lines
1.6 KiB
JSON
{
|
|
"add_bos_token": true,
|
|
"add_prefix_space": false,
|
|
"added_tokens_decoder": {
|
|
"1": {
|
|
"content": "<pad>",
|
|
"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
|
|
},
|
|
"50265": {
|
|
"content": "<|im_start|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"50266": {
|
|
"content": "<|im_end|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"50267": {
|
|
"content": "<|user|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"50268": {
|
|
"content": "<|assistant|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"additional_special_tokens": [
|
|
"<|im_start|>",
|
|
"<|im_end|>",
|
|
"<|user|>",
|
|
"<|assistant|>"
|
|
],
|
|
"bos_token": "</s>",
|
|
"chat_template": "{% for message in messages %}{{'<|im_start|>' + '<|' + message['role'] + '|>' + message['content'] + '<|im_end|>'}}{% endfor %}",
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "</s>",
|
|
"errors": "replace",
|
|
"model_max_length": 1000000000000000019884624838656,
|
|
"pad_token": "<pad>",
|
|
"tokenizer_class": "GPT2Tokenizer",
|
|
"unk_token": "</s>"
|
|
}
|