GeorgeBredis commited on
Commit
d09846e
1 Parent(s): a910956

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 49407,
3
+ "<|startoftext|>": 49406
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json CHANGED
@@ -1,19 +1,28 @@
1
  {
2
- "crop_size": 224,
 
 
 
3
  "do_center_crop": true,
 
4
  "do_normalize": true,
 
5
  "do_resize": true,
6
- "feature_extractor_type": "CLIPFeatureExtractor",
7
  "image_mean": [
8
  0.48145466,
9
  0.4578275,
10
  0.40821073
11
  ],
 
12
  "image_std": [
13
  0.26862954,
14
  0.26130258,
15
  0.27577711
16
  ],
 
17
  "resample": 3,
18
- "size": 224
 
 
 
19
  }
 
1
  {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
  "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
  "do_normalize": true,
9
+ "do_rescale": true,
10
  "do_resize": true,
 
11
  "image_mean": [
12
  0.48145466,
13
  0.4578275,
14
  0.40821073
15
  ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
  "image_std": [
18
  0.26862954,
19
  0.26130258,
20
  0.27577711
21
  ],
22
+ "processor_class": "CLIPProcessor",
23
  "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
  }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|startoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": false
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ }
20
+ },
21
+ "additional_special_tokens": [],
22
+ "bos_token": "<|startoftext|>",
23
+ "clean_up_tokenization_spaces": true,
24
+ "do_lower_case": true,
25
+ "eos_token": "<|endoftext|>",
26
+ "errors": "replace",
27
+ "model_max_length": 77,
28
+ "pad_token": "<|endoftext|>",
29
+ "processor_class": "CLIPProcessor",
30
+ "tokenizer_class": "CLIPTokenizer",
31
+ "tokenizer_file": "/Users/georgebredis/.cache/huggingface/hub/models--laion--CLIP-ViT-B-32-256x256-DataComp-s34B-b86K/snapshots/0e9ac9033bafd4d8d13aa9ce8624a2c7fdc8edca/tokenizer.json",
32
+ "unk_token": "<|endoftext|>"
33
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff