Upload tokenizer
Browse files- special_tokens_map.json +42 -6
- tokenizer.json +2 -2
- tokenizer_config.json +8 -2
special_tokens_map.json
CHANGED
|
@@ -53,9 +53,27 @@
|
|
| 53 |
"gl_ES",
|
| 54 |
"sl_SI"
|
| 55 |
],
|
| 56 |
-
"bos_token":
|
| 57 |
-
|
| 58 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
"mask_token": {
|
| 60 |
"content": "<mask>",
|
| 61 |
"lstrip": true,
|
|
@@ -63,7 +81,25 @@
|
|
| 63 |
"rstrip": false,
|
| 64 |
"single_word": false
|
| 65 |
},
|
| 66 |
-
"pad_token":
|
| 67 |
-
|
| 68 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
}
|
|
|
|
| 53 |
"gl_ES",
|
| 54 |
"sl_SI"
|
| 55 |
],
|
| 56 |
+
"bos_token": {
|
| 57 |
+
"content": "<s>",
|
| 58 |
+
"lstrip": false,
|
| 59 |
+
"normalized": false,
|
| 60 |
+
"rstrip": false,
|
| 61 |
+
"single_word": false
|
| 62 |
+
},
|
| 63 |
+
"cls_token": {
|
| 64 |
+
"content": "<s>",
|
| 65 |
+
"lstrip": false,
|
| 66 |
+
"normalized": false,
|
| 67 |
+
"rstrip": false,
|
| 68 |
+
"single_word": false
|
| 69 |
+
},
|
| 70 |
+
"eos_token": {
|
| 71 |
+
"content": "</s>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false
|
| 76 |
+
},
|
| 77 |
"mask_token": {
|
| 78 |
"content": "<mask>",
|
| 79 |
"lstrip": true,
|
|
|
|
| 81 |
"rstrip": false,
|
| 82 |
"single_word": false
|
| 83 |
},
|
| 84 |
+
"pad_token": {
|
| 85 |
+
"content": "<pad>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false
|
| 90 |
+
},
|
| 91 |
+
"sep_token": {
|
| 92 |
+
"content": "</s>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false
|
| 97 |
+
},
|
| 98 |
+
"unk_token": {
|
| 99 |
+
"content": "<unk>",
|
| 100 |
+
"lstrip": false,
|
| 101 |
+
"normalized": false,
|
| 102 |
+
"rstrip": false,
|
| 103 |
+
"single_word": false
|
| 104 |
+
}
|
| 105 |
}
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e05149e476a633a1848f49e8aab40803980b7a22e1a0829229378759c819049
|
| 3 |
+
size 17094668
|
tokenizer_config.json
CHANGED
|
@@ -515,13 +515,19 @@
|
|
| 515 |
"clean_up_tokenization_spaces": false,
|
| 516 |
"cls_token": "<s>",
|
| 517 |
"eos_token": "</s>",
|
|
|
|
| 518 |
"mask_token": "<mask>",
|
| 519 |
-
"
|
|
|
|
| 520 |
"pad_token": "<pad>",
|
|
|
|
| 521 |
"sep_token": "</s>",
|
| 522 |
"sp_model_kwargs": {},
|
| 523 |
"src_lang": "en_XX",
|
| 524 |
-
"
|
|
|
|
| 525 |
"tokenizer_class": "MBart50Tokenizer",
|
|
|
|
|
|
|
| 526 |
"unk_token": "<unk>"
|
| 527 |
}
|
|
|
|
| 515 |
"clean_up_tokenization_spaces": false,
|
| 516 |
"cls_token": "<s>",
|
| 517 |
"eos_token": "</s>",
|
| 518 |
+
"language_codes": "ML50",
|
| 519 |
"mask_token": "<mask>",
|
| 520 |
+
"max_length": 128,
|
| 521 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 522 |
"pad_token": "<pad>",
|
| 523 |
+
"return_tensors": "pt",
|
| 524 |
"sep_token": "</s>",
|
| 525 |
"sp_model_kwargs": {},
|
| 526 |
"src_lang": "en_XX",
|
| 527 |
+
"stride": 0,
|
| 528 |
+
"tgt_lang": "ar_AR",
|
| 529 |
"tokenizer_class": "MBart50Tokenizer",
|
| 530 |
+
"truncation_side": "right",
|
| 531 |
+
"truncation_strategy": "longest_first",
|
| 532 |
"unk_token": "<unk>"
|
| 533 |
}
|