Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<pad>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -40,7 +40,7 @@
|
|
| 40 |
"eos_token": "</s>",
|
| 41 |
"errors": "replace",
|
| 42 |
"model_max_length": 1000000000000000019884624838656,
|
| 43 |
-
"pad_token": "
|
| 44 |
"tokenizer_class": "GPT2Tokenizer",
|
| 45 |
"unk_token": "<unk>"
|
| 46 |
}
|
|
|
|
| 40 |
"eos_token": "</s>",
|
| 41 |
"errors": "replace",
|
| 42 |
"model_max_length": 1000000000000000019884624838656,
|
| 43 |
+
"pad_token": "<pad>",
|
| 44 |
"tokenizer_class": "GPT2Tokenizer",
|
| 45 |
"unk_token": "<unk>"
|
| 46 |
}
|