low-resource-language-model-adaptation
/
adapted_tokenizers
/added-opt-amh
/opt_100-add_full-amh-opt
/tokenizer_config.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": "ን", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50266": { | |
| "content": "ት", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50267": { | |
| "content": " የ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50268": { | |
| "content": "ው", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50269": { | |
| "content": "ር", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50270": { | |
| "content": "ል", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50271": { | |
| "content": " በ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50272": { | |
| "content": "ም", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50273": { | |
| "content": "ስ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50274": { | |
| "content": " አ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50275": { | |
| "content": "ለ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50276": { | |
| "content": "ች", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50277": { | |
| "content": "ተ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50278": { | |
| "content": "ና", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50279": { | |
| "content": "ያ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50280": { | |
| "content": " እ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50281": { | |
| "content": "ይ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50282": { | |
| "content": "መ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50283": { | |
| "content": "።", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50284": { | |
| "content": "ደ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50285": { | |
| "content": "ረ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50286": { | |
| "content": "ገ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50287": { | |
| "content": " መ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50288": { | |
| "content": "ራ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50289": { | |
| "content": "ድ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50290": { | |
| "content": "ላ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50291": { | |
| "content": "ግ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50292": { | |
| "content": "በ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50293": { | |
| "content": "ታ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50294": { | |
| "content": "ነ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50295": { | |
| "content": "ብ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50296": { | |
| "content": "ማ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50297": { | |
| "content": "ባ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50298": { | |
| "content": "ሚ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50299": { | |
| "content": " ከ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50300": { | |
| "content": "ሰ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50301": { | |
| "content": " ተ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50302": { | |
| "content": "ሪ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50303": { | |
| "content": "ክ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50304": { | |
| "content": " እን", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50305": { | |
| "content": "አ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50306": { | |
| "content": "ቸ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50307": { | |
| "content": "ዳ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50308": { | |
| "content": " ነ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50309": { | |
| "content": "ቀ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50310": { | |
| "content": "ቸው", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50311": { | |
| "content": "ጥ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50312": { | |
| "content": "ፍ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50313": { | |
| "content": " ለ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50314": { | |
| "content": "ዋ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50315": { | |
| "content": "ሉ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50316": { | |
| "content": "ካ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50317": { | |
| "content": "ከ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50318": { | |
| "content": "ህ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50319": { | |
| "content": " ይ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50320": { | |
| "content": "ጠ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50321": { | |
| "content": "ሳ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50322": { | |
| "content": "፡", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50323": { | |
| "content": "ወ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50324": { | |
| "content": " ወ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50325": { | |
| "content": "ቅ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50326": { | |
| "content": "ፈ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50327": { | |
| "content": " ያ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50328": { | |
| "content": "ሆ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50329": { | |
| "content": "የ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50330": { | |
| "content": "ቱ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50331": { | |
| "content": "ጋ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50332": { | |
| "content": " የሚ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50333": { | |
| "content": "ዎች", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50334": { | |
| "content": "ጣ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50335": { | |
| "content": "ሮ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50336": { | |
| "content": "ቶ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50337": { | |
| "content": "ሩ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50338": { | |
| "content": "ኛ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50339": { | |
| "content": "፣", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50340": { | |
| "content": " ስ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50341": { | |
| "content": "ዲ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50342": { | |
| "content": " የተ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50343": { | |
| "content": " ማ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50344": { | |
| "content": " ም", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50345": { | |
| "content": "ዊ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50346": { | |
| "content": " ነው", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50347": { | |
| "content": "ቃ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50348": { | |
| "content": "ዋል", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50349": { | |
| "content": " ሰ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50350": { | |
| "content": " እንደ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50351": { | |
| "content": " ብ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50352": { | |
| "content": "ዮ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50353": { | |
| "content": " ው", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50354": { | |
| "content": " ሲ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50355": { | |
| "content": " ግ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50356": { | |
| "content": "ኑ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50357": { | |
| "content": "ዝ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50358": { | |
| "content": " ላይ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50359": { | |
| "content": " ባ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50360": { | |
| "content": "ሞ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50361": { | |
| "content": " እና", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50362": { | |
| "content": "ዚ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50363": { | |
| "content": "ሁ", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "50364": { | |
| "content": "ነት", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| } | |
| }, | |
| "bos_token": "</s>", | |
| "clean_up_tokenization_spaces": true, | |
| "eos_token": "</s>", | |
| "errors": "replace", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<pad>", | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "unk_token": "</s>" | |
| } | |