Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "</s_answer>": 57523,
+  "</s_question>": 57524,
+  "<no/>": 57525,
+  "<s_answer>": 57526,
+  "<s_docvqa>": 57527,
+  "<s_iitcdip>": 57528,
+  "<s_question>": 57529,
+  "<s_synthdog>": 57530,
+  "<sep/>": 57522,
+  "<yes/>": 57531
+}

config.json

@@ -0,0 +1,190 @@
+{
+  "_name_or_path": "naver-clova-ix/donut-base-finetuned-docvqa",
+  "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": 128,
+    "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": 57532
+  },
+  "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": [
+      2560,
+      1920
+    ],
+    "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0.dev0"
+}

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": "4.33.0.dev0"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145f1bcea8ec0db6bcac30087093781ec29b86dda1b5faad28ce4a5c7009f750
+size 505136232

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863b92e4f0bd48f786a3eefe4f1b996bd18945228c2569985f71405129818e53
+size 505295421

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f93d5f5a2b0d8824f6e46669ac277156807b887c9e2587c95ea70405471370ba
+size 127302452

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd37d20b35e8829714feff5af92e82d07a2331303a0415ab3de2bfc89ab3bb8b
+size 127050973

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daf52060bf59ed395da452c86c970adfab1b45dc27885748ad4a3d13b53b6d9f
+size 471517690

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c58c8012fac23f3cb1aa01962fab5c951524e98142432c664b6d2aa26c5e64e
+size 118537995

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53a8a2102010e6f4c699aa92ab437202aa0a6868113248bca9d6d988f8505691
+size 311503397

onnx/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d6fbd8606261f3c04c9a61a93395647892a0759c48dee64ad701e03928bbf1
+size 91383413

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": 2560,
+    "width": 1920
+  }
+}

quantize_config.json

@@ -0,0 +1,131 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "decoder_model": {
+            "op_types": [
+                "Unsqueeze",
+                "Slice",
+                "Equal",
+                "MatMul",
+                "Sqrt",
+                "Gather",
+                "Add",
+                "ReduceMean",
+                "Softmax",
+                "Where",
+                "Expand",
+                "Shape",
+                "Range",
+                "Constant",
+                "Reshape",
+                "Erf",
+                "Mul",
+                "Cast",
+                "Transpose",
+                "Concat",
+                "Sub",
+                "Squeeze",
+                "Div",
+                "Less",
+                "Pow",
+                "ConstantOfShape"
+            ],
+            "weight_type": "QInt8"
+        },
+        "encoder_model": {
+            "op_types": [
+                "Unsqueeze",
+                "Slice",
+                "MatMul",
+                "Equal",
+                "Sqrt",
+                "Gather",
+                "Add",
+                "ReduceMean",
+                "Softmax",
+                "Where",
+                "Conv",
+                "Expand",
+                "Shape",
+                "Range",
+                "Not",
+                "Constant",
+                "Reshape",
+                "Erf",
+                "Mul",
+                "Cast",
+                "Mod",
+                "Transpose",
+                "ScatterND",
+                "Concat",
+                "Pad",
+                "Sub",
+                "Div",
+                "Pow",
+                "ConstantOfShape"
+            ],
+            "weight_type": "QUInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Unsqueeze",
+                "Slice",
+                "Equal",
+                "MatMul",
+                "Sqrt",
+                "Gather",
+                "Add",
+                "ReduceMean",
+                "Softmax",
+                "Where",
+                "Expand",
+                "Shape",
+                "Range",
+                "If",
+                "Constant",
+                "Reshape",
+                "Erf",
+                "Mul",
+                "Cast",
+                "Transpose",
+                "Concat",
+                "Squeeze",
+                "Sub",
+                "Div",
+                "Less",
+                "Pow",
+                "ConstantOfShape"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_with_past_model": {
+            "op_types": [
+                "Unsqueeze",
+                "Equal",
+                "MatMul",
+                "Sqrt",
+                "Gather",
+                "Add",
+                "ReduceMean",
+                "Softmax",
+                "Where",
+                "Expand",
+                "Shape",
+                "Range",
+                "Constant",
+                "Reshape",
+                "Erf",
+                "Mul",
+                "Cast",
+                "Transpose",
+                "Concat",
+                "Sub",
+                "Div",
+                "Pow",
+                "ConstantOfShape"
+            ],
+            "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 +1,26 @@
+{
+  "additional_special_tokens": [
+    "</s_answer>",
+    "</s_question>",
+    "<no/>",
+    "<s_answer>",
+    "<s_docvqa>",
+    "<s_iitcdip>",
+    "<s_question>",
+    "<s_synthdog>",
+    "<yes/>"
+  ],
+  "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>"
+}