Hugging Face's logo

subhuatharva
/
paligemma_receipts_OCR_dataset

Transformers
Safetensors
Inference Endpoints
Model card Files Community
subhuatharva commited on
Commit
633372f
•
1 Parent(s): f6126bc

Training complete

Browse files
Files changed (5) hide show
  1. added_tokens.json +3 -3
  2. preprocessor_config.json +25 -25
  3. special_tokens_map.json +39 -39
  4. tokenizer.json +2 -2
  5. tokenizer_config.json +0 -0
added_tokens.json CHANGED
@@ -1,3 +1,3 @@
1
- {
2
- "<image>": 257152
3
- }
 
1
+ {
2
+ "<image>": 257152
3
+ }
preprocessor_config.json CHANGED
@@ -1,25 +1,25 @@
1
- {
2
- "do_convert_rgb": null,
3
- "do_normalize": true,
4
- "do_rescale": true,
5
- "do_resize": true,
6
- "image_mean": [
7
- 0.5,
8
- 0.5,
9
- 0.5
10
- ],
11
- "image_processor_type": "SiglipImageProcessor",
12
- "image_seq_length": 256,
13
- "image_std": [
14
- 0.5,
15
- 0.5,
16
- 0.5
17
- ],
18
- "processor_class": "PaliGemmaProcessor",
19
- "resample": 3,
20
- "rescale_factor": 0.00392156862745098,
21
- "size": {
22
- "height": 224,
23
- "width": 224
24
- }
25
- }
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "SiglipImageProcessor",
12
+ "image_seq_length": 256,
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "processor_class": "PaliGemmaProcessor",
19
+ "resample": 3,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 224,
23
+ "width": 224
24
+ }
25
+ }
special_tokens_map.json CHANGED
@@ -1,39 +1,39 @@
1
- {
2
- "additional_special_tokens": [
3
- {
4
- "content": "<image>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- }
10
- ],
11
- "bos_token": {
12
- "content": "<bos>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "eos_token": {
19
- "content": "<eos>",
20
- "lstrip": false,
21
- "normalized": false,
22
- "rstrip": false,
23
- "single_word": false
24
- },
25
- "pad_token": {
26
- "content": "<pad>",
27
- "lstrip": false,
28
- "normalized": false,
29
- "rstrip": false,
30
- "single_word": false
31
- },
32
- "unk_token": {
33
- "content": "<unk>",
34
- "lstrip": false,
35
- "normalized": false,
36
- "rstrip": false,
37
- "single_word": false
38
- }
39
- }
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<image>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<bos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<eos>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<pad>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<unk>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1df2ab04780faccf51a881d7c5a7026cc6f979083af2eebf709d051b8d47134b
3
- size 17763458
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b648d11e0879b11659e6b4051f691752c0cef597a865c6fde5b318b9f68c1d05
3
+ size 34600974
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff