Commit 
							
							·
						
						80bec68
	
1
								Parent(s):
							
							e37f4c9
								
Upload processor
Browse files- preprocessor_config.json +28 -0
 - special_tokens_map.json +7 -0
 - tokenizer.json +0 -0
 - tokenizer_config.json +18 -0
 - vocab.txt +0 -0
 
    	
        preprocessor_config.json
    ADDED
    
    | 
         @@ -0,0 +1,28 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 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": "GIAProcessor",
         
     | 
| 23 | 
         
            +
              "resample": 3,
         
     | 
| 24 | 
         
            +
              "rescale_factor": 0.00392156862745098,
         
     | 
| 25 | 
         
            +
              "size": {
         
     | 
| 26 | 
         
            +
                "shortest_edge": 224
         
     | 
| 27 | 
         
            +
              }
         
     | 
| 28 | 
         
            +
            }
         
     | 
    	
        special_tokens_map.json
    ADDED
    
    | 
         @@ -0,0 +1,7 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "cls_token": "[CLS]",
         
     | 
| 3 | 
         
            +
              "mask_token": "[MASK]",
         
     | 
| 4 | 
         
            +
              "pad_token": "[PAD]",
         
     | 
| 5 | 
         
            +
              "sep_token": "[SEP]",
         
     | 
| 6 | 
         
            +
              "unk_token": "[UNK]"
         
     | 
| 7 | 
         
            +
            }
         
     | 
    	
        tokenizer.json
    ADDED
    
    | 
         The diff for this file is too large to render. 
		See raw diff 
     | 
| 
         | 
    	
        tokenizer_config.json
    ADDED
    
    | 
         @@ -0,0 +1,18 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "clean_up_tokenization_spaces": true,
         
     | 
| 3 | 
         
            +
              "cls_token": "[CLS]",
         
     | 
| 4 | 
         
            +
              "do_lower_case": true,
         
     | 
| 5 | 
         
            +
              "mask_token": "[MASK]",
         
     | 
| 6 | 
         
            +
              "model_input_names": [
         
     | 
| 7 | 
         
            +
                "input_ids",
         
     | 
| 8 | 
         
            +
                "attention_mask"
         
     | 
| 9 | 
         
            +
              ],
         
     | 
| 10 | 
         
            +
              "model_max_length": 512,
         
     | 
| 11 | 
         
            +
              "pad_token": "[PAD]",
         
     | 
| 12 | 
         
            +
              "processor_class": "GIAProcessor",
         
     | 
| 13 | 
         
            +
              "sep_token": "[SEP]",
         
     | 
| 14 | 
         
            +
              "strip_accents": null,
         
     | 
| 15 | 
         
            +
              "tokenize_chinese_chars": true,
         
     | 
| 16 | 
         
            +
              "tokenizer_class": "BertTokenizer",
         
     | 
| 17 | 
         
            +
              "unk_token": "[UNK]"
         
     | 
| 18 | 
         
            +
            }
         
     | 
    	
        vocab.txt
    ADDED
    
    | 
         The diff for this file is too large to render. 
		See raw diff 
     | 
| 
         |