adalbertojunior
commited on
Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +2 -7
- vocab.txt +0 -0
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -44,16 +44,11 @@
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_basic_tokenize": true,
|
47 |
-
"do_lower_case":
|
48 |
"mask_token": "[MASK]",
|
49 |
-
"
|
50 |
-
"input_ids",
|
51 |
-
"attention_mask"
|
52 |
-
],
|
53 |
-
"model_max_length": 512,
|
54 |
"never_split": null,
|
55 |
"pad_token": "[PAD]",
|
56 |
-
"processor_class": "BlipProcessor",
|
57 |
"sep_token": "[SEP]",
|
58 |
"strip_accents": null,
|
59 |
"tokenize_chinese_chars": true,
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
|
|
|
|
|
50 |
"never_split": null,
|
51 |
"pad_token": "[PAD]",
|
|
|
52 |
"sep_token": "[SEP]",
|
53 |
"strip_accents": null,
|
54 |
"tokenize_chinese_chars": true,
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|