thenlpresearcher's picture
thenlpresearcher/finetuned_indictrans2_1
848130e verified
{
"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>",
"extra_special_tokens": {},
"model_max_length": 256,
"pad_token": "<pad>",
"src_vocab_file": "/root/.cache/huggingface/hub/models--ai4bharat--indictrans2-indic-indic-dist-320M/snapshots/ffb7582b6d43791f1fb26b2153fc065f2e9ea575/dict.SRC.json",
"tgt_vocab_file": "/root/.cache/huggingface/hub/models--ai4bharat--indictrans2-indic-indic-dist-320M/snapshots/ffb7582b6d43791f1fb26b2153fc065f2e9ea575/dict.TGT.json",
"tokenizer_class": "IndicTransTokenizer",
"unk_token": "<unk>"
}