252 lines
5.7 KiB
JSON
252 lines
5.7 KiB
JSON
|
|
{
|
||
|
|
"add_bos_token": false,
|
||
|
|
"add_eos_token": false,
|
||
|
|
"add_prefix_space": false,
|
||
|
|
"added_tokens_decoder": {
|
||
|
|
"0": {
|
||
|
|
"content": "<|endoftext|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"1": {
|
||
|
|
"content": "<|padding|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"50254": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50255": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50256": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50257": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50258": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50259": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50260": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50261": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50262": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50263": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50264": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50265": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50266": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50267": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50268": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50269": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50270": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50271": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50272": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50273": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50274": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50275": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50276": {
|
||
|
|
"content": " ",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50277": {
|
||
|
|
"content": "<|pad|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50278": {
|
||
|
|
"content": "<|im_start|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"50279": {
|
||
|
|
"content": "<|im_end|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"50280": {
|
||
|
|
"content": "[PAD]",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"additional_special_tokens": [
|
||
|
|
"<|im_start|>",
|
||
|
|
"<|im_end|>"
|
||
|
|
],
|
||
|
|
"bos_token": "<|im_start|>",
|
||
|
|
"chat_template": "{% 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": true,
|
||
|
|
"eos_token": "<|im_end|>",
|
||
|
|
"model_max_length": 1000000000000000019884624838656,
|
||
|
|
"pad_token": "<|im_end|>",
|
||
|
|
"tokenizer_class": "GPTNeoXTokenizer",
|
||
|
|
"unk_token": "<|endoftext|>"
|
||
|
|
}
|