Transformers update

#4
by RaushanTurganbay HF staff - opened
added_tokens.json CHANGED
@@ -1,3 +1,4 @@
1
  {
 
2
  "[DEC]": 30522
3
  }
 
1
  {
2
+ "<image>": 30523,
3
  "[DEC]": 30522
4
  }
config.json CHANGED
@@ -5,6 +5,7 @@
5
  "image_text_hidden_size": 256,
6
  "initializer_factor": 1.0,
7
  "initializer_range": 0.02,
 
8
  "model_type": "blip-2",
9
  "num_query_tokens": 32,
10
  "qformer_config": {
@@ -16,7 +17,7 @@
16
  "model_type": "opt"
17
  },
18
  "torch_dtype": "float32",
19
- "transformers_version": "4.42.0.dev0",
20
  "use_decoder_only_language_model": true,
21
  "vision_config": {
22
  "image_size": 364,
 
5
  "image_text_hidden_size": 256,
6
  "initializer_factor": 1.0,
7
  "initializer_range": 0.02,
8
+ "image_token_index": 30523,
9
  "model_type": "blip-2",
10
  "num_query_tokens": 32,
11
  "qformer_config": {
 
17
  "model_type": "opt"
18
  },
19
  "torch_dtype": "float32",
20
+ "transformers_version": "4.48.0.dev0",
21
  "use_decoder_only_language_model": true,
22
  "vision_config": {
23
  "image_size": 364,
preprocessor_config.json CHANGED
@@ -1,19 +1,4 @@
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
- "do_convert_rgb",
13
- "return_tensors",
14
- "data_format",
15
- "input_data_format"
16
- ],
17
  "do_convert_rgb": true,
18
  "do_normalize": true,
19
  "do_rescale": true,
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "do_convert_rgb": true,
3
  "do_normalize": true,
4
  "do_rescale": true,
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "num_query_tokens": 32,
3
+ "processor_class": "Blip2Processor"
4
+ }
special_tokens_map.json CHANGED
@@ -6,9 +6,39 @@
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
- "cls_token": "[CLS]",
10
- "mask_token": "[MASK]",
11
- "pad_token": "[PAD]",
12
- "sep_token": "[SEP]",
13
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  }
 
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "[MASK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "[PAD]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "[SEP]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "[UNK]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -47,6 +47,14 @@
47
  "rstrip": false,
48
  "single_word": false,
49
  "special": true
 
 
 
 
 
 
 
 
50
  }
51
  },
52
  "bos_token": "[DEC]",
@@ -54,6 +62,7 @@
54
  "cls_token": "[CLS]",
55
  "do_basic_tokenize": true,
56
  "do_lower_case": true,
 
57
  "mask_token": "[MASK]",
58
  "model_max_length": 512,
59
  "never_split": null,
 
47
  "rstrip": false,
48
  "single_word": false,
49
  "special": true
50
+ },
51
+ "30523": {
52
+ "content": "<image>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
  }
59
  },
60
  "bos_token": "[DEC]",
 
62
  "cls_token": "[CLS]",
63
  "do_basic_tokenize": true,
64
  "do_lower_case": true,
65
+ "extra_special_tokens": {},
66
  "mask_token": "[MASK]",
67
  "model_max_length": 512,
68
  "never_split": null,