Upload processor
Browse files- merges.txt +0 -0
- preprocessor_config.json +19 -0
- special_tokens_map.json +1 -9
- tokenizer.json +0 -0
- tokenizer_config.json +9 -9
- vocab.json +0 -0
merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_resize": true,
|
| 4 |
+
"feature_extractor_type": "ViltFeatureExtractor",
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_std": [
|
| 11 |
+
0.5,
|
| 12 |
+
0.5,
|
| 13 |
+
0.5
|
| 14 |
+
],
|
| 15 |
+
"processor_class": "ViltProcessor",
|
| 16 |
+
"resample": 3,
|
| 17 |
+
"size": 384,
|
| 18 |
+
"size_divisor": 32
|
| 19 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -1,14 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "<s>",
|
| 3 |
"cls_token": "<s>",
|
| 4 |
-
"
|
| 5 |
-
"mask_token": {
|
| 6 |
-
"content": "<mask>",
|
| 7 |
-
"lstrip": true,
|
| 8 |
-
"normalized": true,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false
|
| 11 |
-
},
|
| 12 |
"pad_token": "<pad>",
|
| 13 |
"sep_token": "</s>",
|
| 14 |
"unk_token": "<unk>"
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"cls_token": "<s>",
|
| 3 |
+
"mask_token": "<mask>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"pad_token": "<pad>",
|
| 5 |
"sep_token": "</s>",
|
| 6 |
"unk_token": "<unk>"
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,16 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"bos_token": "<s>",
|
| 4 |
"cls_token": "<s>",
|
| 5 |
-
"
|
| 6 |
-
"errors": "replace",
|
| 7 |
"mask_token": "<mask>",
|
| 8 |
-
"model_max_length":
|
| 9 |
-
"name_or_path": "Bingsu/
|
| 10 |
"pad_token": "<pad>",
|
|
|
|
| 11 |
"sep_token": "</s>",
|
| 12 |
-
"special_tokens_map_file": "
|
| 13 |
-
"
|
| 14 |
-
"
|
|
|
|
|
|
|
| 15 |
"unk_token": "<unk>"
|
| 16 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"cls_token": "<s>",
|
| 3 |
+
"do_lower_case": true,
|
|
|
|
| 4 |
"mask_token": "<mask>",
|
| 5 |
+
"model_max_length": 512,
|
| 6 |
+
"name_or_path": "Bingsu/my_vilt_b32_mlm_not_trained",
|
| 7 |
"pad_token": "<pad>",
|
| 8 |
+
"processor_class": "ViltProcessor",
|
| 9 |
"sep_token": "</s>",
|
| 10 |
+
"special_tokens_map_file": "ko_BBPE_tokenizer_bert2\\special_tokens_map.json",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"trust_remote_code": false,
|
| 15 |
"unk_token": "<unk>"
|
| 16 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|