Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,22 @@
+{
+  "</s_date>": 57539,
+  "</s_destination_station>": 57537,
+  "</s_name>": 57535,
+  "</s_seat_category>": 57533,
+  "</s_starting_station>": 57531,
+  "</s_ticket_num>": 57529,
+  "</s_ticket_rates>": 57527,
+  "</s_train_num>": 57525,
+  "<s_date>": 57540,
+  "<s_destination_station>": 57538,
+  "<s_iitcdip>": 57523,
+  "<s_name>": 57536,
+  "<s_seat_category>": 57534,
+  "<s_starting_station>": 57532,
+  "<s_synthdog>": 57524,
+  "<s_ticket_num>": 57530,
+  "<s_ticket_rates>": 57528,
+  "<s_train_num>": 57526,
+  "<s_zhtrainticket>": 57541,
+  "<sep/>": 57522
+}

config.json

@@ -0,0 +1,189 @@
+{
+  "_name_or_path": "naver-clova-ix/donut-base-finetuned-zhtrainticket",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "add_final_layer_norm": true,
+    "architectures": null,
+    "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": 4,
+    "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,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 256,
+    "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": true,
+    "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": 57542
+  },
+  "encoder": {
+    "_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,
+      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": [
+      960,
+      1280
+    ],
+    "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": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_absolute_embeddings": false,
+    "use_bfloat16": false,
+    "window_size": 10
+  },
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "tie_word_embeddings": false,
+  "transformers_version": "4.33.2"
+}

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": "4.33.2"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96943bc7f01ec1fe0cf9a329eb3cec218b62090bab9ee10c0da6e6af8572f953
+size 505701480

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08b42bb49e155fe39c5026920514693b2120a7dccba789fbff01ce543146ef6
+size 505860669

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85487e7f035fbb71bfc989c950fafd624eb5b5af238c62f7c3739a734efed6db
+size 127177316

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a1868399fb0209e7fdc8027eb904aceedad23a93560015510b048720dfeb940
+size 126925837

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea7189816d83dbc928dc35394388a923009ea5c1ea80183518de9b87aa922d6
+size 472082938

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97d50440004bca1c7ee6e41aa8ccadb119963dcccff7d96f79ba84163aa6d1c1
+size 118453859

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc094c4b8a4c9fb5fcf94e9be0b6fa071b1c6bafa305268ae7c44f672dc3226
+size 311503397

onnx/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4ff3f5efab0e24fd481673f7604420c1dac4b3708e70ca18f127c7be6082d4
+size 90924606

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "do_align_long_axis": false,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_thumbnail": true,
+  "feature_extractor_type": "DonutFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "DonutFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "DonutProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 960,
+    "width": 1280
+  }
+}

quantize_config.json

@@ -0,0 +1,131 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "decoder_with_past_model": {
+            "op_types": [
+                "MatMul",
+                "Shape",
+                "Where",
+                "Add",
+                "Gather",
+                "Pow",
+                "Transpose",
+                "Sub",
+                "Equal",
+                "Unsqueeze",
+                "Div",
+                "ConstantOfShape",
+                "Sqrt",
+                "Softmax",
+                "Expand",
+                "Erf",
+                "ReduceMean",
+                "Range",
+                "Mul",
+                "Reshape",
+                "Concat",
+                "Cast",
+                "Constant"
+            ],
+            "weight_type": "QInt8"
+        },
+        "encoder_model": {
+            "op_types": [
+                "MatMul",
+                "Shape",
+                "Where",
+                "Slice",
+                "Add",
+                "Gather",
+                "Transpose",
+                "Pow",
+                "Sub",
+                "Equal",
+                "Not",
+                "ScatterND",
+                "Conv",
+                "Unsqueeze",
+                "Mod",
+                "Div",
+                "Sqrt",
+                "ConstantOfShape",
+                "Softmax",
+                "Expand",
+                "Erf",
+                "ReduceMean",
+                "Range",
+                "Mul",
+                "Reshape",
+                "Concat",
+                "Cast",
+                "Pad",
+                "Constant"
+            ],
+            "weight_type": "QUInt8"
+        },
+        "decoder_model": {
+            "op_types": [
+                "MatMul",
+                "Shape",
+                "Where",
+                "Slice",
+                "Add",
+                "Gather",
+                "Pow",
+                "Transpose",
+                "Sub",
+                "Equal",
+                "Unsqueeze",
+                "Div",
+                "ConstantOfShape",
+                "Sqrt",
+                "Softmax",
+                "Expand",
+                "Squeeze",
+                "Erf",
+                "ReduceMean",
+                "Range",
+                "Mul",
+                "Reshape",
+                "Concat",
+                "Cast",
+                "Less",
+                "Constant"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "MatMul",
+                "Shape",
+                "Where",
+                "Slice",
+                "Add",
+                "Gather",
+                "Pow",
+                "Transpose",
+                "If",
+                "Sub",
+                "Equal",
+                "Unsqueeze",
+                "Div",
+                "ConstantOfShape",
+                "Sqrt",
+                "Softmax",
+                "Expand",
+                "Squeeze",
+                "Erf",
+                "ReduceMean",
+                "Range",
+                "Mul",
+                "Reshape",
+                "Concat",
+                "Cast",
+                "Less",
+                "Constant"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
+size 1296245

special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": [
+    "<s_zhtrainticket>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}