Commit
•
c88bf23
1
Parent(s):
2574123
Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer_config.json +11 -1
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,11 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"cls_token": "<s>",
|
| 4 |
"eos_token": "</s>",
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<s>",
|
| 4 |
+
"<pad>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"<unk>",
|
| 7 |
+
"<mask>"
|
| 8 |
+
],
|
| 9 |
"bos_token": "<s>",
|
| 10 |
"cls_token": "<s>",
|
| 11 |
"eos_token": "</s>",
|
tokenizer_config.json
CHANGED
|
@@ -42,17 +42,27 @@
|
|
| 42 |
"special": true
|
| 43 |
}
|
| 44 |
},
|
| 45 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
"bos_token": "<s>",
|
| 47 |
"clean_up_tokenization_spaces": true,
|
| 48 |
"cls_token": "<s>",
|
| 49 |
"eos_token": "</s>",
|
| 50 |
"errors": "replace",
|
| 51 |
"mask_token": "<mask>",
|
|
|
|
| 52 |
"model_max_length": 512,
|
| 53 |
"pad_token": "<pad>",
|
| 54 |
"sep_token": "</s>",
|
|
|
|
| 55 |
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
"trim_offsets": true,
|
|
|
|
|
|
|
| 57 |
"unk_token": "<unk>"
|
| 58 |
}
|
|
|
|
| 42 |
"special": true
|
| 43 |
}
|
| 44 |
},
|
| 45 |
+
"additional_special_tokens": [
|
| 46 |
+
"<s>",
|
| 47 |
+
"<pad>",
|
| 48 |
+
"</s>",
|
| 49 |
+
"<unk>",
|
| 50 |
+
"<mask>"
|
| 51 |
+
],
|
| 52 |
"bos_token": "<s>",
|
| 53 |
"clean_up_tokenization_spaces": true,
|
| 54 |
"cls_token": "<s>",
|
| 55 |
"eos_token": "</s>",
|
| 56 |
"errors": "replace",
|
| 57 |
"mask_token": "<mask>",
|
| 58 |
+
"max_length": 128,
|
| 59 |
"model_max_length": 512,
|
| 60 |
"pad_token": "<pad>",
|
| 61 |
"sep_token": "</s>",
|
| 62 |
+
"stride": 0,
|
| 63 |
"tokenizer_class": "RobertaTokenizer",
|
| 64 |
"trim_offsets": true,
|
| 65 |
+
"truncation_side": "right",
|
| 66 |
+
"truncation_strategy": "longest_first",
|
| 67 |
"unk_token": "<unk>"
|
| 68 |
}
|