cstr commited on
Commit
8b46517
1 Parent(s): e7e102b

Upload 4 files

Browse files
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfa7dae3b7caabbdfd569cc48edc55283b31a6a56a3befb699bc7b9526961f77
3
+ size 2585112
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "additional_special_tokens": ["__en__", "__ha__", "__is__", "__ja__", "__cs__", "__ru__", "__zh__", "__de__"]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"src_lang": "en", "tgt_lang": null, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "language_codes": "wmt21", "num_madeup_words": 0, "additional_special_tokens": ["__en__", "__ha__", "__is__", "__ja__", "__cs__", "__ru__", "__zh__", "__de__"], "tokenizer_class": "M2M100Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff