ColPali
Safetensors
English
paligemma
vidore-experimental
tonywu71 michaelfeil commited on
Commit
cd80ee4
1 Parent(s): dce8522

add_configs (#2)

Browse files

- Create preprocessor_config.json (9c21d7fc50bc6004f54839b484b228e065754ded)
- Upload tokenizer.json (fed2b059bd3ba52760a44a34a9e22a4317b286ca)
- Upload 2 files (88bd6ac6722131e60b3ac627cb14f6861867d44b)


Co-authored-by: Michael <[email protected]>

.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
preprocessor_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_rescale",
8
+ "rescale_factor",
9
+ "do_normalize",
10
+ "image_mean",
11
+ "image_std",
12
+ "return_tensors",
13
+ "data_format",
14
+ "input_data_format",
15
+ "do_convert_rgb"
16
+ ],
17
+ "do_convert_rgb": null,
18
+ "do_normalize": true,
19
+ "do_rescale": true,
20
+ "do_resize": true,
21
+ "image_mean": [
22
+ 0.5,
23
+ 0.5,
24
+ 0.5
25
+ ],
26
+ "image_processor_type": "SiglipImageProcessor",
27
+ "image_seq_length": 1024,
28
+ "image_std": [
29
+ 0.5,
30
+ 0.5,
31
+ 0.5
32
+ ],
33
+ "processor_class": "PaliGemmaProcessor",
34
+ "resample": 3,
35
+ "rescale_factor": 0.00392156862745098,
36
+ "size": {
37
+ "height": 448,
38
+ "width": 448
39
+ }
40
+ }
special_tokens_map.json ADDED
@@ -0,0 +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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffd310e50986db7a039948ab83441d612689e7f989198e31b5c8984ca458adf6
3
+ size 17763459
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff