initial commit

added_tokens.json

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

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": 128,
+  "max_position_embeddings": 128,
+  "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 sha256:6c7b40074bc43cde8ec5097a3b1acd0c0e83fa506478739af34c8722cadbc0e8
+size 1012719683

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_answer>", "</s_question>", "<no/>", "<s_answer>", "<s_docvqa>", "<s_iitcdip>", "<s_question>", "<s_synthdog>", "<yes/>"]}

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"}