| { |
| "added_tokens_decoder": { |
| "0": { |
| "content": "<s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "1": { |
| "content": "<pad>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "2": { |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "3": { |
| "content": "<unk>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "auto_map": { |
| "AutoTokenizer": [ |
| "tokenization_indictrans.IndicTransTokenizer", |
| null |
| ] |
| }, |
| "bos_token": "<s>", |
| "clean_up_tokenization_spaces": true, |
| "do_lower_case": false, |
| "eos_token": "</s>", |
| "model_max_length": 256, |
| "pad_token": "<pad>", |
| "src_vocab_file": "/media/bigdata/71ec9ff9-bdc2-410a-bfcb-1a3e24aaf8f7/sagar/legal_language_translation/codes/experimentation/MoE_Inclusion_2/outputs_indictrans2_finetune/best/dict.SRC.json", |
| "tgt_vocab_file": "/media/bigdata/71ec9ff9-bdc2-410a-bfcb-1a3e24aaf8f7/sagar/legal_language_translation/codes/experimentation/MoE_Inclusion_2/outputs_indictrans2_finetune/best/dict.TGT.json", |
| "tokenizer_class": "IndicTransTokenizer", |
| "unk_token": "<unk>" |
| } |
|
|
