Upload tokenizer
Browse files- tokenizer.json +9 -0
- tokenizer_config.json +1 -8
tokenizer.json
CHANGED
|
@@ -11,6 +11,15 @@
|
|
| 11 |
"rstrip": false,
|
| 12 |
"normalized": true,
|
| 13 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
}
|
| 15 |
],
|
| 16 |
"normalizer": null,
|
|
|
|
| 11 |
"rstrip": false,
|
| 12 |
"normalized": true,
|
| 13 |
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 50257,
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
}
|
| 24 |
],
|
| 25 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
|
@@ -6,15 +6,8 @@
|
|
| 6 |
"errors": "replace",
|
| 7 |
"is_local": false,
|
| 8 |
"local_files_only": false,
|
| 9 |
-
"max_length": 128,
|
| 10 |
"model_max_length": 1024,
|
| 11 |
-
"
|
| 12 |
-
"pad_token": "<|endoftext|>",
|
| 13 |
-
"pad_token_type_id": 0,
|
| 14 |
-
"padding_side": "right",
|
| 15 |
-
"stride": 0,
|
| 16 |
"tokenizer_class": "GPT2Tokenizer",
|
| 17 |
-
"truncation_side": "right",
|
| 18 |
-
"truncation_strategy": "longest_first",
|
| 19 |
"unk_token": "<|endoftext|>"
|
| 20 |
}
|
|
|
|
| 6 |
"errors": "replace",
|
| 7 |
"is_local": false,
|
| 8 |
"local_files_only": false,
|
|
|
|
| 9 |
"model_max_length": 1024,
|
| 10 |
+
"pad_token": "[PAD]",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
|
|
| 12 |
"unk_token": "<|endoftext|>"
|
| 13 |
}
|