1168 lines
26 KiB
JSON
1168 lines
26 KiB
JSON
|
|
{
|
||
|
|
"add_bos_token": false,
|
||
|
|
"add_prefix_space": false,
|
||
|
|
"added_tokens_decoder": {
|
||
|
|
"50256": {
|
||
|
|
"content": "<|endoftext|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"50257": {
|
||
|
|
"content": "<|extratoken_1|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50258": {
|
||
|
|
"content": "<|extratoken_2|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50259": {
|
||
|
|
"content": "<|extratoken_3|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50260": {
|
||
|
|
"content": "<|extratoken_4|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50261": {
|
||
|
|
"content": "<|extratoken_5|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50262": {
|
||
|
|
"content": "<|extratoken_6|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50263": {
|
||
|
|
"content": "<|extratoken_7|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50264": {
|
||
|
|
"content": "<|extratoken_8|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50265": {
|
||
|
|
"content": "<|extratoken_9|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50266": {
|
||
|
|
"content": "<|extratoken_10|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50267": {
|
||
|
|
"content": "<|extratoken_11|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50268": {
|
||
|
|
"content": "<|extratoken_12|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50269": {
|
||
|
|
"content": "<|extratoken_13|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50270": {
|
||
|
|
"content": "<|extratoken_14|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50271": {
|
||
|
|
"content": "<|extratoken_15|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50272": {
|
||
|
|
"content": "<|extratoken_16|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50273": {
|
||
|
|
"content": "<|extratoken_17|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50274": {
|
||
|
|
"content": "<|extratoken_18|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50275": {
|
||
|
|
"content": "<|extratoken_19|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50276": {
|
||
|
|
"content": "<|extratoken_20|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50277": {
|
||
|
|
"content": "<|extratoken_21|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50278": {
|
||
|
|
"content": "<|extratoken_22|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50279": {
|
||
|
|
"content": "<|extratoken_23|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50280": {
|
||
|
|
"content": "<|extratoken_24|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50281": {
|
||
|
|
"content": "<|extratoken_25|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50282": {
|
||
|
|
"content": "<|extratoken_26|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50283": {
|
||
|
|
"content": "<|extratoken_27|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50284": {
|
||
|
|
"content": "<|extratoken_28|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50285": {
|
||
|
|
"content": "<|extratoken_29|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50286": {
|
||
|
|
"content": "<|extratoken_30|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50287": {
|
||
|
|
"content": "<|extratoken_31|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50288": {
|
||
|
|
"content": "<|extratoken_32|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50289": {
|
||
|
|
"content": "<|extratoken_33|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50290": {
|
||
|
|
"content": "<|extratoken_34|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50291": {
|
||
|
|
"content": "<|extratoken_35|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50292": {
|
||
|
|
"content": "<|extratoken_36|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50293": {
|
||
|
|
"content": "<|extratoken_37|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50294": {
|
||
|
|
"content": "<|extratoken_38|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50295": {
|
||
|
|
"content": "<|extratoken_39|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50296": {
|
||
|
|
"content": "<|extratoken_40|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50297": {
|
||
|
|
"content": "<|extratoken_41|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50298": {
|
||
|
|
"content": "<|extratoken_42|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50299": {
|
||
|
|
"content": "<|extratoken_43|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50300": {
|
||
|
|
"content": "<|extratoken_44|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50301": {
|
||
|
|
"content": "<|extratoken_45|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50302": {
|
||
|
|
"content": "<|extratoken_46|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50303": {
|
||
|
|
"content": "<|extratoken_47|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50304": {
|
||
|
|
"content": "<|extratoken_48|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50305": {
|
||
|
|
"content": "<|extratoken_49|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50306": {
|
||
|
|
"content": "<|extratoken_50|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50307": {
|
||
|
|
"content": "<|extratoken_51|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50308": {
|
||
|
|
"content": "<|extratoken_52|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50309": {
|
||
|
|
"content": "<|extratoken_53|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50310": {
|
||
|
|
"content": "<|extratoken_54|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50311": {
|
||
|
|
"content": "<|extratoken_55|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50312": {
|
||
|
|
"content": "<|extratoken_56|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50313": {
|
||
|
|
"content": "<|extratoken_57|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50314": {
|
||
|
|
"content": "<|extratoken_58|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50315": {
|
||
|
|
"content": "<|extratoken_59|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50316": {
|
||
|
|
"content": "<|extratoken_60|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50317": {
|
||
|
|
"content": "<|extratoken_61|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50318": {
|
||
|
|
"content": "<|extratoken_62|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50319": {
|
||
|
|
"content": "<|extratoken_63|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50320": {
|
||
|
|
"content": "<|extratoken_64|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50321": {
|
||
|
|
"content": "<|extratoken_65|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50322": {
|
||
|
|
"content": "<|extratoken_66|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50323": {
|
||
|
|
"content": "<|extratoken_67|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50324": {
|
||
|
|
"content": "<|extratoken_68|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50325": {
|
||
|
|
"content": "<|extratoken_69|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50326": {
|
||
|
|
"content": "<|extratoken_70|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50327": {
|
||
|
|
"content": "<|extratoken_71|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50328": {
|
||
|
|
"content": "<|extratoken_72|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50329": {
|
||
|
|
"content": "<|extratoken_73|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50330": {
|
||
|
|
"content": "<|extratoken_74|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50331": {
|
||
|
|
"content": "<|extratoken_75|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50332": {
|
||
|
|
"content": "<|extratoken_76|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50333": {
|
||
|
|
"content": "<|extratoken_77|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50334": {
|
||
|
|
"content": "<|extratoken_78|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50335": {
|
||
|
|
"content": "<|extratoken_79|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50336": {
|
||
|
|
"content": "<|extratoken_80|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50337": {
|
||
|
|
"content": "<|extratoken_81|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50338": {
|
||
|
|
"content": "<|extratoken_82|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50339": {
|
||
|
|
"content": "<|extratoken_83|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50340": {
|
||
|
|
"content": "<|extratoken_84|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50341": {
|
||
|
|
"content": "<|extratoken_85|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50342": {
|
||
|
|
"content": "<|extratoken_86|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50343": {
|
||
|
|
"content": "<|extratoken_87|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50344": {
|
||
|
|
"content": "<|extratoken_88|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50345": {
|
||
|
|
"content": "<|extratoken_89|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50346": {
|
||
|
|
"content": "<|extratoken_90|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50347": {
|
||
|
|
"content": "<|extratoken_91|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50348": {
|
||
|
|
"content": "<|extratoken_92|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50349": {
|
||
|
|
"content": "<|extratoken_93|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50350": {
|
||
|
|
"content": "<|extratoken_94|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50351": {
|
||
|
|
"content": "<|extratoken_95|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50352": {
|
||
|
|
"content": "<|extratoken_96|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50353": {
|
||
|
|
"content": "<|extratoken_97|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50354": {
|
||
|
|
"content": "<|extratoken_98|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50355": {
|
||
|
|
"content": "<|extratoken_99|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50356": {
|
||
|
|
"content": "<|extratoken_100|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50357": {
|
||
|
|
"content": "<|extratoken_101|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50358": {
|
||
|
|
"content": "<|extratoken_102|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50359": {
|
||
|
|
"content": "<|extratoken_103|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50360": {
|
||
|
|
"content": "<|extratoken_104|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50361": {
|
||
|
|
"content": "<|extratoken_105|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50362": {
|
||
|
|
"content": "<|extratoken_106|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50363": {
|
||
|
|
"content": "<|extratoken_107|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50364": {
|
||
|
|
"content": "<|extratoken_108|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50365": {
|
||
|
|
"content": "<|extratoken_109|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50366": {
|
||
|
|
"content": "<|extratoken_110|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50367": {
|
||
|
|
"content": "<|extratoken_111|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50368": {
|
||
|
|
"content": "<|extratoken_112|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50369": {
|
||
|
|
"content": "<|extratoken_113|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50370": {
|
||
|
|
"content": "<|extratoken_114|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50371": {
|
||
|
|
"content": "<|extratoken_115|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50372": {
|
||
|
|
"content": "<|extratoken_116|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50373": {
|
||
|
|
"content": "<|extratoken_117|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50374": {
|
||
|
|
"content": "<|extratoken_118|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50375": {
|
||
|
|
"content": "<|extratoken_119|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50376": {
|
||
|
|
"content": "<|extratoken_120|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50377": {
|
||
|
|
"content": "<|extratoken_121|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50378": {
|
||
|
|
"content": "<|extratoken_122|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50379": {
|
||
|
|
"content": "<|extratoken_123|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50380": {
|
||
|
|
"content": "<|extratoken_124|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50381": {
|
||
|
|
"content": "<|extratoken_125|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50382": {
|
||
|
|
"content": "<|extratoken_126|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50383": {
|
||
|
|
"content": "<|extratoken_127|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50384": {
|
||
|
|
"content": "<|extratoken_128|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50385": {
|
||
|
|
"content": "<|extratoken_129|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50386": {
|
||
|
|
"content": "<|extratoken_130|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50387": {
|
||
|
|
"content": "<|extratoken_131|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50388": {
|
||
|
|
"content": "<|extratoken_132|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50389": {
|
||
|
|
"content": "<|extratoken_133|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50390": {
|
||
|
|
"content": "<|extratoken_134|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50391": {
|
||
|
|
"content": "<|extratoken_135|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50392": {
|
||
|
|
"content": "<|extratoken_136|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50393": {
|
||
|
|
"content": "<|extratoken_137|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50394": {
|
||
|
|
"content": "<|extratoken_138|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50395": {
|
||
|
|
"content": "<|extratoken_139|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50396": {
|
||
|
|
"content": "<|extratoken_140|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50397": {
|
||
|
|
"content": "<|extratoken_141|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50398": {
|
||
|
|
"content": "<|extratoken_142|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
},
|
||
|
|
"50399": {
|
||
|
|
"content": "<|extratoken_143|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": false
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"bos_token": "<|endoftext|>",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"eos_token": "<|endoftext|>",
|
||
|
|
"errors": "replace",
|
||
|
|
"extra_special_tokens": {},
|
||
|
|
"model_max_length": 2048,
|
||
|
|
"pad_token": "<|endoftext|>",
|
||
|
|
"tokenizer_class": "GPT2Tokenizer",
|
||
|
|
"unk_token": "<|endoftext|>"
|
||
|
|
}
|