Commit
•
e35e892
1
Parent(s):
996d1b3
Upload processor
Browse files- preprocessor_config.json +17 -1
- processor_config.json +6 -0
- special_tokens_map.json +7 -1
- tokenizer.json +1 -0
- tokenizer_config.json +1 -0
preprocessor_config.json
CHANGED
@@ -1,4 +1,21 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"crop_size": {
|
3 |
"height": 336,
|
4 |
"width": 336
|
@@ -8,7 +25,6 @@
|
|
8 |
"do_normalize": true,
|
9 |
"do_rescale": true,
|
10 |
"do_resize": true,
|
11 |
-
"feature_extractor_type": "CLIPFeatureExtractor",
|
12 |
"image_mean": [
|
13 |
0.48145466,
|
14 |
0.4578275,
|
|
|
1 |
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_center_crop",
|
8 |
+
"crop_size",
|
9 |
+
"do_rescale",
|
10 |
+
"rescale_factor",
|
11 |
+
"do_normalize",
|
12 |
+
"image_mean",
|
13 |
+
"image_std",
|
14 |
+
"do_convert_rgb",
|
15 |
+
"return_tensors",
|
16 |
+
"data_format",
|
17 |
+
"input_data_format"
|
18 |
+
],
|
19 |
"crop_size": {
|
20 |
"height": 336,
|
21 |
"width": 336
|
|
|
25 |
"do_normalize": true,
|
26 |
"do_rescale": true,
|
27 |
"do_resize": true,
|
|
|
28 |
"image_mean": [
|
29 |
0.48145466,
|
30 |
0.4578275,
|
processor_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"image_token": "<image>",
|
3 |
+
"patch_size": 14,
|
4 |
+
"processor_class": "LlavaProcessor",
|
5 |
+
"vision_feature_select_strategy": "default"
|
6 |
+
}
|
special_tokens_map.json
CHANGED
@@ -13,7 +13,13 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
"unk_token": {
|
24 |
"content": "<unk>",
|
25 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -152,6 +152,7 @@
|
|
152 |
"end_of_word_suffix": null,
|
153 |
"fuse_unk": true,
|
154 |
"byte_fallback": true,
|
|
|
155 |
"vocab": {
|
156 |
"<unk>": 0,
|
157 |
"<s>": 1,
|
|
|
152 |
"end_of_word_suffix": null,
|
153 |
"fuse_unk": true,
|
154 |
"byte_fallback": true,
|
155 |
+
"ignore_merges": false,
|
156 |
"vocab": {
|
157 |
"<unk>": 0,
|
158 |
"<s>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|