Add files using upload-large-folder tool

README.md

@@ -0,0 +1,3 @@
+---
+license: cc-by-nc-sa-4.0
+---

config.json

@@ -0,0 +1,267 @@
+{
+  "_name_or_path": "datalab-to/layout_order_hr3",
+  "architectures": [
+    "SuryaLayoutModel"
+  ],
+  "decoder": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_window_size": 16,
+    "aux_heads": 0,
+    "bad_words_ids": null,
+    "bbox_size": 1024,
+    "begin_suppress_tokens": null,
+    "block_types": [
+      "attention"
+    ],
+    "bos_token_id": 1,
+    "causal": true,
+    "chunk_size_feed_forward": 0,
+    "conv1d_width": 4,
+    "cross_attention_hidden_size": null,
+    "cross_attn_layers": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9
+    ],
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "double_residual_flow": true,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_cross_attn_layers": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9
+    ],
+    "encoder_hidden_size": 1024,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1,
+    "exponential_decay_length_penalty": null,
+    "final_w_init_variance_scale": 0.2,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "global_attn_layers": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9
+    ],
+    "head_dim": 64,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 512,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "img_size_bucket": 100,
+    "init_std": 0.02,
+    "intermediate_size": 2048,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "label_count": 20,
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "logits_soft_cap": 30.0,
+    "lru_width": 512,
+    "max_length": 20,
+    "max_pause_tokens": 0,
+    "min_length": 0,
+    "model_type": "surya_layout",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 8,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 10,
+    "num_key_value_heads": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "pause_token_count": 0,
+    "pause_token_id": 2,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 10000.0,
+    "self_attn_layers": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9
+    ],
+    "sep_token_id": null,
+    "skew_scaler": 512,
+    "special_token_count": 3,
+    "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": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 1025,
+    "w_init_variance_scale": 0.01
+  },
+  "decoder_end_token_id": 1,
+  "decoder_start_token_id": 1,
+  "encoder": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "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,
+      12,
+      2
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "early_stopping": false,
+    "embed_dim": 128,
+    "encoder_length": 1024,
+    "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": [
+      768,
+      768
+    ],
+    "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_kv_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,
+    "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": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_absolute_embeddings": false,
+    "use_bfloat16": false,
+    "use_positional_embeddings": true,
+    "window_size": 8
+  },
+  "eos_token_id": 1,
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.1"
+}

manifest.json

@@ -0,0 +1 @@
+{"files": ["model.safetensors", "config.json", "README.md", ".gitattributes", "preprocessor_config.json"]}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae53c6e227d20e4241d285dac162c6ff04fa5c63e168a36e667749cb3566936
+size 252815964

preprocessor_config.json

@@ -0,0 +1,33 @@
+{
+  "do_align_long_axis": false,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_thumbnail": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SuryaEncoderImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_size": {
+    "height": 768,
+    "width": 768
+  },
+  "patch_size": [
+    4,
+    4
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 2560,
+    "width": 1920
+  }
+}