Upload 7 files
Browse files- config.json +190 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +27 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,190 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "architectures": [
         | 
| 3 | 
            +
                "VisionEncoderDecoderModel"
         | 
| 4 | 
            +
              ],
         | 
| 5 | 
            +
              "decoder": {
         | 
| 6 | 
            +
                "_attn_implementation_autoset": true,
         | 
| 7 | 
            +
                "_name_or_path": "",
         | 
| 8 | 
            +
                "activation_dropout": 0.0,
         | 
| 9 | 
            +
                "activation_function": "gelu",
         | 
| 10 | 
            +
                "add_cross_attention": true,
         | 
| 11 | 
            +
                "add_final_layer_norm": true,
         | 
| 12 | 
            +
                "architectures": null,
         | 
| 13 | 
            +
                "attention_dropout": 0.0,
         | 
| 14 | 
            +
                "bad_words_ids": null,
         | 
| 15 | 
            +
                "begin_suppress_tokens": null,
         | 
| 16 | 
            +
                "bos_token_id": 0,
         | 
| 17 | 
            +
                "chunk_size_feed_forward": 0,
         | 
| 18 | 
            +
                "classifier_dropout": 0.0,
         | 
| 19 | 
            +
                "cross_attention_hidden_size": null,
         | 
| 20 | 
            +
                "d_model": 1024,
         | 
| 21 | 
            +
                "decoder_attention_heads": 16,
         | 
| 22 | 
            +
                "decoder_ffn_dim": 4096,
         | 
| 23 | 
            +
                "decoder_layerdrop": 0.0,
         | 
| 24 | 
            +
                "decoder_layers": 10,
         | 
| 25 | 
            +
                "decoder_start_token_id": null,
         | 
| 26 | 
            +
                "diversity_penalty": 0.0,
         | 
| 27 | 
            +
                "do_sample": false,
         | 
| 28 | 
            +
                "dropout": 0.1,
         | 
| 29 | 
            +
                "early_stopping": false,
         | 
| 30 | 
            +
                "encoder_attention_heads": 16,
         | 
| 31 | 
            +
                "encoder_ffn_dim": 4096,
         | 
| 32 | 
            +
                "encoder_layerdrop": 0.0,
         | 
| 33 | 
            +
                "encoder_layers": 12,
         | 
| 34 | 
            +
                "encoder_no_repeat_ngram_size": 0,
         | 
| 35 | 
            +
                "eos_token_id": 2,
         | 
| 36 | 
            +
                "exponential_decay_length_penalty": null,
         | 
| 37 | 
            +
                "finetuning_task": null,
         | 
| 38 | 
            +
                "forced_bos_token_id": null,
         | 
| 39 | 
            +
                "forced_eos_token_id": 2,
         | 
| 40 | 
            +
                "id2label": {
         | 
| 41 | 
            +
                  "0": "LABEL_0",
         | 
| 42 | 
            +
                  "1": "LABEL_1"
         | 
| 43 | 
            +
                },
         | 
| 44 | 
            +
                "init_std": 0.02,
         | 
| 45 | 
            +
                "is_decoder": true,
         | 
| 46 | 
            +
                "is_encoder_decoder": false,
         | 
| 47 | 
            +
                "label2id": {
         | 
| 48 | 
            +
                  "LABEL_0": 0,
         | 
| 49 | 
            +
                  "LABEL_1": 1
         | 
| 50 | 
            +
                },
         | 
| 51 | 
            +
                "length_penalty": 1.0,
         | 
| 52 | 
            +
                "max_length": 20,
         | 
| 53 | 
            +
                "max_position_embeddings": 4096,
         | 
| 54 | 
            +
                "min_length": 0,
         | 
| 55 | 
            +
                "model_type": "mbart",
         | 
| 56 | 
            +
                "no_repeat_ngram_size": 0,
         | 
| 57 | 
            +
                "num_beam_groups": 1,
         | 
| 58 | 
            +
                "num_beams": 1,
         | 
| 59 | 
            +
                "num_hidden_layers": 12,
         | 
| 60 | 
            +
                "num_return_sequences": 1,
         | 
| 61 | 
            +
                "output_attentions": false,
         | 
| 62 | 
            +
                "output_hidden_states": false,
         | 
| 63 | 
            +
                "output_scores": false,
         | 
| 64 | 
            +
                "pad_token_id": 1,
         | 
| 65 | 
            +
                "prefix": null,
         | 
| 66 | 
            +
                "problem_type": null,
         | 
| 67 | 
            +
                "pruned_heads": {},
         | 
| 68 | 
            +
                "remove_invalid_values": false,
         | 
| 69 | 
            +
                "repetition_penalty": 1.0,
         | 
| 70 | 
            +
                "return_dict": true,
         | 
| 71 | 
            +
                "return_dict_in_generate": false,
         | 
| 72 | 
            +
                "scale_embedding": true,
         | 
| 73 | 
            +
                "sep_token_id": null,
         | 
| 74 | 
            +
                "suppress_tokens": null,
         | 
| 75 | 
            +
                "task_specific_params": null,
         | 
| 76 | 
            +
                "temperature": 1.0,
         | 
| 77 | 
            +
                "tf_legacy_loss": false,
         | 
| 78 | 
            +
                "tie_encoder_decoder": false,
         | 
| 79 | 
            +
                "tie_word_embeddings": false,
         | 
| 80 | 
            +
                "tokenizer_class": null,
         | 
| 81 | 
            +
                "top_k": 50,
         | 
| 82 | 
            +
                "top_p": 1.0,
         | 
| 83 | 
            +
                "torch_dtype": null,
         | 
| 84 | 
            +
                "torchscript": false,
         | 
| 85 | 
            +
                "typical_p": 1.0,
         | 
| 86 | 
            +
                "use_bfloat16": false,
         | 
| 87 | 
            +
                "use_cache": true,
         | 
| 88 | 
            +
                "vocab_size": 73921
         | 
| 89 | 
            +
              },
         | 
| 90 | 
            +
              "encoder": {
         | 
| 91 | 
            +
                "_attn_implementation_autoset": true,
         | 
| 92 | 
            +
                "_name_or_path": "",
         | 
| 93 | 
            +
                "add_cross_attention": false,
         | 
| 94 | 
            +
                "architectures": null,
         | 
| 95 | 
            +
                "attention_probs_dropout_prob": 0.0,
         | 
| 96 | 
            +
                "bad_words_ids": null,
         | 
| 97 | 
            +
                "begin_suppress_tokens": null,
         | 
| 98 | 
            +
                "bos_token_id": null,
         | 
| 99 | 
            +
                "chunk_size_feed_forward": 0,
         | 
| 100 | 
            +
                "cross_attention_hidden_size": null,
         | 
| 101 | 
            +
                "decoder_start_token_id": null,
         | 
| 102 | 
            +
                "depths": [
         | 
| 103 | 
            +
                  2,
         | 
| 104 | 
            +
                  2,
         | 
| 105 | 
            +
                  14,
         | 
| 106 | 
            +
                  2
         | 
| 107 | 
            +
                ],
         | 
| 108 | 
            +
                "diversity_penalty": 0.0,
         | 
| 109 | 
            +
                "do_sample": false,
         | 
| 110 | 
            +
                "drop_path_rate": 0.1,
         | 
| 111 | 
            +
                "early_stopping": false,
         | 
| 112 | 
            +
                "embed_dim": 128,
         | 
| 113 | 
            +
                "encoder_no_repeat_ngram_size": 0,
         | 
| 114 | 
            +
                "eos_token_id": null,
         | 
| 115 | 
            +
                "exponential_decay_length_penalty": null,
         | 
| 116 | 
            +
                "finetuning_task": null,
         | 
| 117 | 
            +
                "forced_bos_token_id": null,
         | 
| 118 | 
            +
                "forced_eos_token_id": null,
         | 
| 119 | 
            +
                "hidden_act": "gelu",
         | 
| 120 | 
            +
                "hidden_dropout_prob": 0.0,
         | 
| 121 | 
            +
                "hidden_size": 1024,
         | 
| 122 | 
            +
                "id2label": {
         | 
| 123 | 
            +
                  "0": "LABEL_0",
         | 
| 124 | 
            +
                  "1": "LABEL_1"
         | 
| 125 | 
            +
                },
         | 
| 126 | 
            +
                "image_size": [
         | 
| 127 | 
            +
                  896,
         | 
| 128 | 
            +
                  896
         | 
| 129 | 
            +
                ],
         | 
| 130 | 
            +
                "initializer_range": 0.02,
         | 
| 131 | 
            +
                "is_decoder": false,
         | 
| 132 | 
            +
                "is_encoder_decoder": false,
         | 
| 133 | 
            +
                "label2id": {
         | 
| 134 | 
            +
                  "LABEL_0": 0,
         | 
| 135 | 
            +
                  "LABEL_1": 1
         | 
| 136 | 
            +
                },
         | 
| 137 | 
            +
                "layer_norm_eps": 1e-05,
         | 
| 138 | 
            +
                "length_penalty": 1.0,
         | 
| 139 | 
            +
                "max_length": 20,
         | 
| 140 | 
            +
                "min_length": 0,
         | 
| 141 | 
            +
                "mlp_ratio": 4.0,
         | 
| 142 | 
            +
                "model_type": "donut-swin",
         | 
| 143 | 
            +
                "no_repeat_ngram_size": 0,
         | 
| 144 | 
            +
                "num_beam_groups": 1,
         | 
| 145 | 
            +
                "num_beams": 1,
         | 
| 146 | 
            +
                "num_channels": 3,
         | 
| 147 | 
            +
                "num_heads": [
         | 
| 148 | 
            +
                  4,
         | 
| 149 | 
            +
                  8,
         | 
| 150 | 
            +
                  16,
         | 
| 151 | 
            +
                  32
         | 
| 152 | 
            +
                ],
         | 
| 153 | 
            +
                "num_layers": 4,
         | 
| 154 | 
            +
                "num_return_sequences": 1,
         | 
| 155 | 
            +
                "output_attentions": false,
         | 
| 156 | 
            +
                "output_hidden_states": false,
         | 
| 157 | 
            +
                "output_scores": false,
         | 
| 158 | 
            +
                "pad_token_id": null,
         | 
| 159 | 
            +
                "patch_size": 4,
         | 
| 160 | 
            +
                "prefix": null,
         | 
| 161 | 
            +
                "problem_type": null,
         | 
| 162 | 
            +
                "pruned_heads": {},
         | 
| 163 | 
            +
                "qkv_bias": true,
         | 
| 164 | 
            +
                "remove_invalid_values": false,
         | 
| 165 | 
            +
                "repetition_penalty": 1.0,
         | 
| 166 | 
            +
                "return_dict": true,
         | 
| 167 | 
            +
                "return_dict_in_generate": false,
         | 
| 168 | 
            +
                "sep_token_id": null,
         | 
| 169 | 
            +
                "suppress_tokens": null,
         | 
| 170 | 
            +
                "task_specific_params": null,
         | 
| 171 | 
            +
                "temperature": 1.0,
         | 
| 172 | 
            +
                "tf_legacy_loss": false,
         | 
| 173 | 
            +
                "tie_encoder_decoder": false,
         | 
| 174 | 
            +
                "tie_word_embeddings": true,
         | 
| 175 | 
            +
                "tokenizer_class": null,
         | 
| 176 | 
            +
                "top_k": 50,
         | 
| 177 | 
            +
                "top_p": 1.0,
         | 
| 178 | 
            +
                "torch_dtype": null,
         | 
| 179 | 
            +
                "torchscript": false,
         | 
| 180 | 
            +
                "typical_p": 1.0,
         | 
| 181 | 
            +
                "use_absolute_embeddings": false,
         | 
| 182 | 
            +
                "use_bfloat16": false,
         | 
| 183 | 
            +
                "window_size": 7
         | 
| 184 | 
            +
              },
         | 
| 185 | 
            +
              "is_encoder_decoder": true,
         | 
| 186 | 
            +
              "model_type": "vision-encoder-decoder",
         | 
| 187 | 
            +
              "tie_word_embeddings": false,
         | 
| 188 | 
            +
              "torch_dtype": "float16",
         | 
| 189 | 
            +
              "transformers_version": "4.47.0"
         | 
| 190 | 
            +
            }
         | 
    	
        generation_config.json
    ADDED
    
    | @@ -0,0 +1,8 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_from_model_config": true,
         | 
| 3 | 
            +
              "bos_token_id": 0,
         | 
| 4 | 
            +
              "eos_token_id": 2,
         | 
| 5 | 
            +
              "forced_eos_token_id": 2,
         | 
| 6 | 
            +
              "pad_token_id": 1,
         | 
| 7 | 
            +
              "transformers_version": "4.47.0"
         | 
| 8 | 
            +
            }
         | 
    	
        model.safetensors
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:bfe37dc90e7455688e65ae902b34c259c89f250b6223663a2fcdee4375618a7e
         | 
| 3 | 
            +
            size 795822904
         | 
    	
        preprocessor_config.json
    ADDED
    
    | @@ -0,0 +1,27 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "do_align_long_axis": true,
         | 
| 3 | 
            +
              "do_crop_margin": false,
         | 
| 4 | 
            +
              "do_normalize": true,
         | 
| 5 | 
            +
              "do_pad": true,
         | 
| 6 | 
            +
              "do_rescale": true,
         | 
| 7 | 
            +
              "do_resize": true,
         | 
| 8 | 
            +
              "do_thumbnail": true,
         | 
| 9 | 
            +
              "image_mean": [
         | 
| 10 | 
            +
                0.485,
         | 
| 11 | 
            +
                0.456,
         | 
| 12 | 
            +
                0.406
         | 
| 13 | 
            +
              ],
         | 
| 14 | 
            +
              "image_processor_type": "DonutImageProcessor",
         | 
| 15 | 
            +
              "image_std": [
         | 
| 16 | 
            +
                0.229,
         | 
| 17 | 
            +
                0.224,
         | 
| 18 | 
            +
                0.225
         | 
| 19 | 
            +
              ],
         | 
| 20 | 
            +
              "processor_class": "DonutProcessor",
         | 
| 21 | 
            +
              "resample": 2,
         | 
| 22 | 
            +
              "rescale_factor": 0.00392156862745098,
         | 
| 23 | 
            +
              "size": {
         | 
| 24 | 
            +
                "height": 896,
         | 
| 25 | 
            +
                "width": 896
         | 
| 26 | 
            +
              }
         | 
| 27 | 
            +
            }
         | 
    	
        special_tokens_map.json
    ADDED
    
    | @@ -0,0 +1,15 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "additional_special_tokens": [
         | 
| 3 | 
            +
                {
         | 
| 4 | 
            +
                  "content": " <Answer/>",
         | 
| 5 | 
            +
                  "lstrip": false,
         | 
| 6 | 
            +
                  "normalized": false,
         | 
| 7 | 
            +
                  "rstrip": false,
         | 
| 8 | 
            +
                  "single_word": false
         | 
| 9 | 
            +
                }
         | 
| 10 | 
            +
              ],
         | 
| 11 | 
            +
              "bos_token": "<s>",
         | 
| 12 | 
            +
              "eos_token": "</s>",
         | 
| 13 | 
            +
              "pad_token": "<pad>",
         | 
| 14 | 
            +
              "unk_token": "<unk>"
         | 
| 15 | 
            +
            }
         | 
    	
        tokenizer.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        tokenizer_config.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
