Update tokenizer_config.json
Browse files- tokenizer_config.json +10 -1
tokenizer_config.json
CHANGED
|
@@ -26,6 +26,14 @@
|
|
| 26 |
"rstrip": false,
|
| 27 |
"single_word": false,
|
| 28 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
}
|
| 30 |
},
|
| 31 |
"additional_special_tokens": [],
|
|
@@ -35,7 +43,8 @@
|
|
| 35 |
"extra_special_tokens": {},
|
| 36 |
"legacy": false,
|
| 37 |
"model_max_length": 2048,
|
| 38 |
-
"pad_token":
|
|
|
|
| 39 |
"sp_model_kwargs": {},
|
| 40 |
"spaces_between_special_tokens": false,
|
| 41 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 26 |
"rstrip": false,
|
| 27 |
"single_word": false,
|
| 28 |
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
}
|
| 38 |
},
|
| 39 |
"additional_special_tokens": [],
|
|
|
|
| 43 |
"extra_special_tokens": {},
|
| 44 |
"legacy": false,
|
| 45 |
"model_max_length": 2048,
|
| 46 |
+
"pad_token": "[PAD]",
|
| 47 |
+
"padding_side": "right",
|
| 48 |
"sp_model_kwargs": {},
|
| 49 |
"spaces_between_special_tokens": false,
|
| 50 |
"tokenizer_class": "LlamaTokenizer",
|