initial commit

added_tokens.json

@@ -0,0 +1 @@
+{"<sep/>": 57522, "</s_class>": 57523, "<advertisement/>": 57524, "<budget/>": 57525, "<email/>": 57526, "<file_folder/>": 57527, "<form/>": 57528, "<handwritten/>": 57529, "<invoice/>": 57530, "<letter/>": 57531, "<memo/>": 57532, "<news_article/>": 57533, "<presentation/>": 57534, "<questionnaire/>": 57535, "<resume/>": 57536, "<s_class>": 57537, "<s_iitcdip>": 57538, "<s_rvlcdip>": 57539, "<s_synthdog>": 57540, "<scientific_publication/>": 57541, "<scientific_report/>": 57542, "<specification/>": 57543}

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "naver-clova-ix/donut-base",
+  "align_long_axis": false,
+  "architectures": [
+    "DonutModel"
+  ],
+  "decoder_layer": 4,
+  "encoder_layer": [
+    2,
+    2,
+    14,
+    2
+  ],
+  "input_size": [
+    2560,
+    1920
+  ],
+  "max_length": 8,
+  "max_position_embeddings": 8,
+  "model_type": "donut",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "window_size": 10
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c017dfaaa742078b13267bc89a880f76825af51eeec916076b013f8b6e6956c3
+size 1012277315

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 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["</s_class>", "<advertisement/>", "<budget/>", "<email/>", "<file_folder/>", "<form/>", "<handwritten/>", "<invoice/>", "<letter/>", "<memo/>", "<news_article/>", "<presentation/>", "<questionnaire/>", "<resume/>", "<s_class>", "<s_iitcdip>", "<s_rvlcdip>", "<s_synthdog>", "<scientific_publication/>", "<scientific_report/>", "<specification/>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/213c2041358e63047b407f94cde1ae23904d31a3bceb57eab291028c1e949437.7135a4b25ac726e19641f0d68803ff02bad960d6319064f55fa9c536929b86fc", "name_or_path": "hyunwoongko/asian-bart-ecjk", "tokenizer_class": "XLMRobertaTokenizer"}