|
{
|
|
"add_prefix_space": false,
|
|
"added_tokens_decoder": {
|
|
"100256": {
|
|
"content": "<|dummy_0|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100257": {
|
|
"content": "<|endoftext|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100258": {
|
|
"content": "<|fim_prefix|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100259": {
|
|
"content": "<|fim_middle|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100260": {
|
|
"content": "<|fim_suffix|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100261": {
|
|
"content": "<|dummy_1|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100262": {
|
|
"content": "<|dummy_2|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100263": {
|
|
"content": "<|dummy_3|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100264": {
|
|
"content": "<|im_start|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100265": {
|
|
"content": "<|im_end|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100266": {
|
|
"content": "<|im_sep|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100267": {
|
|
"content": "<|dummy_4|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100268": {
|
|
"content": "<|dummy_5|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100269": {
|
|
"content": "<|dummy_6|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100270": {
|
|
"content": "<|dummy_7|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100271": {
|
|
"content": "<|dummy_8|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100272": {
|
|
"content": "<|dummy_9|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100273": {
|
|
"content": "<|dummy_10|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100274": {
|
|
"content": "<|dummy_11|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100275": {
|
|
"content": "<|dummy_12|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100276": {
|
|
"content": "<|endofprompt|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100277": {
|
|
"content": "<|dummy_13|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100278": {
|
|
"content": "<|dummy_14|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100279": {
|
|
"content": "<|dummy_15|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100280": {
|
|
"content": "<|dummy_16|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100281": {
|
|
"content": "<|dummy_17|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100282": {
|
|
"content": "<|dummy_18|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100283": {
|
|
"content": "<|dummy_19|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100284": {
|
|
"content": "<|dummy_20|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100285": {
|
|
"content": "<|dummy_21|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100286": {
|
|
"content": "<|dummy_22|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100287": {
|
|
"content": "<|dummy_23|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100288": {
|
|
"content": "<|dummy_24|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100289": {
|
|
"content": "<|dummy_25|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100290": {
|
|
"content": "<|dummy_26|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100291": {
|
|
"content": "<|dummy_27|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100292": {
|
|
"content": "<|dummy_28|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100293": {
|
|
"content": "<|dummy_29|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100294": {
|
|
"content": "<|dummy_30|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100295": {
|
|
"content": "<|dummy_31|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100296": {
|
|
"content": "<|dummy_32|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100297": {
|
|
"content": "<|dummy_33|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100298": {
|
|
"content": "<|dummy_34|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100299": {
|
|
"content": "<|dummy_35|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100300": {
|
|
"content": "<|dummy_36|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100301": {
|
|
"content": "<|dummy_37|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100302": {
|
|
"content": "<|dummy_38|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100303": {
|
|
"content": "<|dummy_39|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100304": {
|
|
"content": "<|dummy_40|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100305": {
|
|
"content": "<|dummy_41|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100306": {
|
|
"content": "<|dummy_42|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100307": {
|
|
"content": "<|dummy_43|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100308": {
|
|
"content": "<|dummy_44|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100309": {
|
|
"content": "<|dummy_45|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100310": {
|
|
"content": "<|dummy_46|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100311": {
|
|
"content": "<|dummy_47|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100312": {
|
|
"content": "<|dummy_48|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100313": {
|
|
"content": "<|dummy_49|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100314": {
|
|
"content": "<|dummy_50|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100315": {
|
|
"content": "<|dummy_51|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100316": {
|
|
"content": "<|dummy_52|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100317": {
|
|
"content": "<|dummy_53|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100318": {
|
|
"content": "<|dummy_54|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100319": {
|
|
"content": "<|dummy_55|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100320": {
|
|
"content": "<|dummy_56|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100321": {
|
|
"content": "<|dummy_57|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100322": {
|
|
"content": "<|dummy_58|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100323": {
|
|
"content": "<|dummy_59|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100324": {
|
|
"content": "<|dummy_60|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100325": {
|
|
"content": "<|dummy_61|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100326": {
|
|
"content": "<|dummy_62|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100327": {
|
|
"content": "<|dummy_63|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100328": {
|
|
"content": "<|dummy_64|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100329": {
|
|
"content": "<|dummy_65|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100330": {
|
|
"content": "<|dummy_66|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100331": {
|
|
"content": "<|dummy_67|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100332": {
|
|
"content": "<|dummy_68|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100333": {
|
|
"content": "<|dummy_69|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100334": {
|
|
"content": "<|dummy_70|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100335": {
|
|
"content": "<|dummy_71|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100336": {
|
|
"content": "<|dummy_72|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100337": {
|
|
"content": "<|dummy_73|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100338": {
|
|
"content": "<|dummy_74|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100339": {
|
|
"content": "<|dummy_75|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100340": {
|
|
"content": "<|dummy_76|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100341": {
|
|
"content": "<|dummy_77|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100342": {
|
|
"content": "<|dummy_78|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100343": {
|
|
"content": "<|dummy_79|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100344": {
|
|
"content": "<|dummy_80|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100345": {
|
|
"content": "<|dummy_81|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100346": {
|
|
"content": "<|dummy_82|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100347": {
|
|
"content": "<|dummy_83|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100348": {
|
|
"content": "<|dummy_84|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100349": {
|
|
"content": "<|dummy_85|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100350": {
|
|
"content": "<|dummy_86|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"100351": {
|
|
"content": "<|dummy_87|>",
|
|
"lstrip": true,
|
|
"normalized": false,
|
|
"rstrip": true,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"bos_token": "<|endoftext|>",
|
|
"chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|><|im_start|>assistant<|im_sep|>'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}",
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|endoftext|>",
|
|
"extra_special_tokens": {},
|
|
"model_max_length": 16384,
|
|
"pad_token": "<|endoftext|>",
|
|
"tokenizer_class": "GPT2Tokenizer",
|
|
"unk_token": "<|endoftext|>"
|
|
}
|
|
|