Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+hub/models--vikp--surya_det3/blobs/5a2a74e413345541b7ca0db0cb1d41785649eb99fe6a1b5166aa8bd7c0a8881d filter=lfs diff=lfs merge=lfs -text
+hub/models--vikp--surya_layout3/blobs/64a74e7f804289d76c13f7aab35ad32c6071ccb41db04d8626909c84063971b4 filter=lfs diff=lfs merge=lfs -text
+hub/models--vikp--surya_order/blobs/d6688651c37649cc60492f18b5e6bf085f852e0f05e0543b6ca57f25fa884b4a filter=lfs diff=lfs merge=lfs -text
+hub/models--vikp--surya_rec2/blobs/9a75b64cbeaed06820559bcda4e12c1235de62b5bce787d57cf56a9c3a7123d1 filter=lfs diff=lfs merge=lfs -text
+hub/models--vikp--surya_tablerec/blobs/59a0e54bb3f1ccc8313ed1a75035435e477773ecc62cc1bb0cee0e5dc58889c8 filter=lfs diff=lfs merge=lfs -text
+hub/models--vikp--texify/blobs/c4eed27b2bbeb493d7fbba31feda6af5c7527246a35a96d49eaa1010f9c7e9af filter=lfs diff=lfs merge=lfs -text

hub/models--vikp--surya_det3/blobs/17579df25d3b063dedb036aaca5b495efe5088b8

@@ -0,0 +1,39 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "segmentation_maps",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_reduce_labels",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_reduce_labels": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "SegformerImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 1200,
+    "width": 1200
+  }
+}

hub/models--vikp--surya_det3/blobs/5a2a74e413345541b7ca0db0cb1d41785649eb99fe6a1b5166aa8bd7c0a8881d

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a2a74e413345541b7ca0db0cb1d41785649eb99fe6a1b5166aa8bd7c0a8881d
+size 153827656

hub/models--vikp--surya_det3/blobs/9888778190fd6ecff72bde2ecab5b24cda345851

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "vikp/line_detector_3",
+  "architectures": [
+    "EfficientViTForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.0,
+  "decoder_hidden_size": 512,
+  "decoder_layer_hidden_size": 128,
+  "depths": [
+    1,
+    1,
+    1,
+    6,
+    6
+  ],
+  "head_dim": 32,
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    32,
+    64,
+    160,
+    256
+  ],
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-06,
+  "model_type": "efficientvit",
+  "num_channels": 3,
+  "num_classes": 2,
+  "num_stages": 4,
+  "patch_size": [
+    7,
+    7
+  ],
+  "semantic_loss_ignore_index": -1,
+  "strides": [
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "widths": [
+    32,
+    64,
+    128,
+    256,
+    512
+  ]
+}

hub/models--vikp--surya_det3/refs/main

@@ -0,0 +1 @@
+467ee9ec33e6e6c5f73e57dbc1415b14032f5b95

hub/models--vikp--surya_det3/snapshots/467ee9ec33e6e6c5f73e57dbc1415b14032f5b95/config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "vikp/line_detector_3",
+  "architectures": [
+    "EfficientViTForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.0,
+  "decoder_hidden_size": 512,
+  "decoder_layer_hidden_size": 128,
+  "depths": [
+    1,
+    1,
+    1,
+    6,
+    6
+  ],
+  "head_dim": 32,
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    32,
+    64,
+    160,
+    256
+  ],
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-06,
+  "model_type": "efficientvit",
+  "num_channels": 3,
+  "num_classes": 2,
+  "num_stages": 4,
+  "patch_size": [
+    7,
+    7
+  ],
+  "semantic_loss_ignore_index": -1,
+  "strides": [
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "widths": [
+    32,
+    64,
+    128,
+    256,
+    512
+  ]
+}

hub/models--vikp--surya_det3/snapshots/467ee9ec33e6e6c5f73e57dbc1415b14032f5b95/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a2a74e413345541b7ca0db0cb1d41785649eb99fe6a1b5166aa8bd7c0a8881d
+size 153827656

hub/models--vikp--surya_det3/snapshots/467ee9ec33e6e6c5f73e57dbc1415b14032f5b95/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "segmentation_maps",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_reduce_labels",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_reduce_labels": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "SegformerImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 1200,
+    "width": 1200
+  }
+}

hub/models--vikp--surya_layout3/blobs/2cd406fa7808c997daa69ef095b1992f243dadd7

@@ -0,0 +1,23 @@
+{
+  "do_normalize": true,
+  "do_reduce_labels": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "SegformerImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 1024,
+    "width": 1024
+  }
+}

hub/models--vikp--surya_layout3/blobs/64a74e7f804289d76c13f7aab35ad32c6071ccb41db04d8626909c84063971b4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a74e7f804289d76c13f7aab35ad32c6071ccb41db04d8626909c84063971b4
+size 153848176

hub/models--vikp--surya_layout3/blobs/afaa751c9f40e9df6796a7c2f3d7a9a2159ccae0

@@ -0,0 +1,80 @@
+{
+  "_name_or_path": "vikp/layout4",
+  "architectures": [
+    "EfficientViTForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.0,
+  "decoder_hidden_size": 512,
+  "decoder_layer_hidden_size": 128,
+  "depths": [
+    1,
+    1,
+    1,
+    6,
+    6
+  ],
+  "head_dim": 32,
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    32,
+    64,
+    160,
+    256
+  ],
+  "id2label": {
+    "0": "Blank",
+    "1": "Caption",
+    "2": "Footnote",
+    "3": "Formula",
+    "4": "List-item",
+    "5": "Page-footer",
+    "6": "Page-header",
+    "7": "Picture",
+    "8": "Section-header",
+    "9": "Table",
+    "10": "Text",
+    "11": "Title"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Blank": 0,
+    "Caption": 1,
+    "Footnote": 2,
+    "Formula": 3,
+    "List-item": 4,
+    "Page-footer": 5,
+    "Page-header": 6,
+    "Picture": 7,
+    "Section-header": 8,
+    "Table": 9,
+    "Text": 10,
+    "Title": 11
+  },
+  "layer_norm_eps": 1e-06,
+  "model_type": "efficientvit",
+  "num_channels": 3,
+  "num_classes": 2,
+  "num_stages": 4,
+  "patch_size": [
+    7,
+    7
+  ],
+  "semantic_loss_ignore_index": -1,
+  "strides": [
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "widths": [
+    32,
+    64,
+    128,
+    256,
+    512
+  ]
+}

hub/models--vikp--surya_layout3/refs/main

@@ -0,0 +1 @@
+6f4c319b213ddbe736c9fe6de87ad7dc3bbb0a1e

hub/models--vikp--surya_layout3/snapshots/6f4c319b213ddbe736c9fe6de87ad7dc3bbb0a1e/config.json

@@ -0,0 +1,80 @@
+{
+  "_name_or_path": "vikp/layout4",
+  "architectures": [
+    "EfficientViTForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.0,
+  "decoder_hidden_size": 512,
+  "decoder_layer_hidden_size": 128,
+  "depths": [
+    1,
+    1,
+    1,
+    6,
+    6
+  ],
+  "head_dim": 32,
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    32,
+    64,
+    160,
+    256
+  ],
+  "id2label": {
+    "0": "Blank",
+    "1": "Caption",
+    "2": "Footnote",
+    "3": "Formula",
+    "4": "List-item",
+    "5": "Page-footer",
+    "6": "Page-header",
+    "7": "Picture",
+    "8": "Section-header",
+    "9": "Table",
+    "10": "Text",
+    "11": "Title"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Blank": 0,
+    "Caption": 1,
+    "Footnote": 2,
+    "Formula": 3,
+    "List-item": 4,
+    "Page-footer": 5,
+    "Page-header": 6,
+    "Picture": 7,
+    "Section-header": 8,
+    "Table": 9,
+    "Text": 10,
+    "Title": 11
+  },
+  "layer_norm_eps": 1e-06,
+  "model_type": "efficientvit",
+  "num_channels": 3,
+  "num_classes": 2,
+  "num_stages": 4,
+  "patch_size": [
+    7,
+    7
+  ],
+  "semantic_loss_ignore_index": -1,
+  "strides": [
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "widths": [
+    32,
+    64,
+    128,
+    256,
+    512
+  ]
+}

hub/models--vikp--surya_layout3/snapshots/6f4c319b213ddbe736c9fe6de87ad7dc3bbb0a1e/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a74e7f804289d76c13f7aab35ad32c6071ccb41db04d8626909c84063971b4
+size 153848176

hub/models--vikp--surya_layout3/snapshots/6f4c319b213ddbe736c9fe6de87ad7dc3bbb0a1e/preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_normalize": true,
+  "do_reduce_labels": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "SegformerImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 1024,
+    "width": 1024
+  }
+}

hub/models--vikp--surya_order/blobs/4566f6f099f2c8ff7426500ff4a7d84a7a8514a0

@@ -0,0 +1,199 @@
+{
+  "_name_or_path": "vikp/order_hr",
+  "architectures": [
+    "OrderVisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "add_final_layer_norm": true,
+    "architectures": [
+      "MBartForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 3,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": 2,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "kv_heads": 4,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_height": 1285,
+    "max_length": 20,
+    "max_position_embeddings": 1536,
+    "max_target_positions": 517,
+    "max_width": 1285,
+    "min_length": 0,
+    "model_type": "mbart",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": true,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 261
+  },
+  "encoder": {
+    "_name_or_path": "vikp/donut-encoder",
+    "add_cross_attention": false,
+    "architectures": [
+      "DonutSwinModel"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      2,
+      2,
+      14,
+      2
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "early_stopping": false,
+    "embed_dim": 128,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": [
+      1024,
+      1024
+    ],
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 4.0,
+    "model_type": "donut-swin",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_layers": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 4,
+    "path_norm": true,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_2d_embeddings": false,
+    "use_absolute_embeddings": true,
+    "use_bfloat16": false,
+    "window_size": 7
+  },
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2"
+}

hub/models--vikp--surya_order/blobs/bb3f109ce8d6999ebfda8fbe7940ce7e68ea7e60

@@ -0,0 +1,39 @@
+{
+  "box_pad_id": 1001,
+  "box_size": {
+    "height": 1024,
+    "width": 1024
+  },
+  "do_align_long_axis": false,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_reduce_labels": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_thumbnail": true,
+  "feature_extractor_type": "SegformerFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "OrderImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "max_boxes": 255,
+  "patch_size": [
+    4,
+    4
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 1024,
+    "width": 1024
+  },
+  "token_pad_id": 1282,
+  "token_sep_id": 1281
+}

hub/models--vikp--surya_order/blobs/cda4db4b7f886de50399b061100af28767cf2b71

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.36.2"
+}

hub/models--vikp--surya_order/blobs/d6688651c37649cc60492f18b5e6bf085f852e0f05e0543b6ca57f25fa884b4a

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6688651c37649cc60492f18b5e6bf085f852e0f05e0543b6ca57f25fa884b4a
+size 550040752

hub/models--vikp--surya_order/refs/main

@@ -0,0 +1 @@
+7b727d0a2c942cdc8596d186115f65c12c812bd8

hub/models--vikp--surya_order/snapshots/7b727d0a2c942cdc8596d186115f65c12c812bd8/config.json

@@ -0,0 +1,199 @@
+{
+  "_name_or_path": "vikp/order_hr",
+  "architectures": [
+    "OrderVisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "add_final_layer_norm": true,
+    "architectures": [
+      "MBartForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 3,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": 2,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "kv_heads": 4,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_height": 1285,
+    "max_length": 20,
+    "max_position_embeddings": 1536,
+    "max_target_positions": 517,
+    "max_width": 1285,
+    "min_length": 0,
+    "model_type": "mbart",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": true,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 261
+  },
+  "encoder": {
+    "_name_or_path": "vikp/donut-encoder",
+    "add_cross_attention": false,
+    "architectures": [
+      "DonutSwinModel"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      2,
+      2,
+      14,
+      2
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "early_stopping": false,
+    "embed_dim": 128,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": [
+      1024,
+      1024
+    ],
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 4.0,
+    "model_type": "donut-swin",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_layers": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 4,
+    "path_norm": true,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_2d_embeddings": false,
+    "use_absolute_embeddings": true,
+    "use_bfloat16": false,
+    "window_size": 7
+  },
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2"
+}

hub/models--vikp--surya_order/snapshots/7b727d0a2c942cdc8596d186115f65c12c812bd8/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.36.2"
+}

hub/models--vikp--surya_order/snapshots/7b727d0a2c942cdc8596d186115f65c12c812bd8/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6688651c37649cc60492f18b5e6bf085f852e0f05e0543b6ca57f25fa884b4a
+size 550040752