Upload tokenizer
Browse files- special_tokens_map.json +9 -1
- tokenizer.json +0 -0
- tokenizer_config.json +5 -0
special_tokens_map.json
CHANGED
@@ -1 +1,9 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": {
|
3 |
+
"content": "[PAD]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
}
|
9 |
+
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -43,6 +43,11 @@
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": false,
|
45 |
"extra_special_tokens": {},
|
|
|
46 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
|
|
|
|
|
47 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
48 |
}
|
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": false,
|
45 |
"extra_special_tokens": {},
|
46 |
+
"max_length": null,
|
47 |
"model_max_length": 1000000000000000019884624838656,
|
48 |
+
"pad_to_multiple_of": null,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"pad_token_type_id": 0,
|
51 |
+
"padding_side": "right",
|
52 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
53 |
}
|