init

.gitattributes

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,3 @@
+---
+license: mit
+---

added_tokens.json

@@ -0,0 +1,110 @@
+{
+  "<s_iitcdip>": 57523,
+  "<s_lavibe-base>": 57525,
+  "<s_synthdog>": 57524,
+  "<sep/>": 57522,
+  "伪": 57619,
+  "估": 57528,
+  "俞": 57598,
+  "债": 57610,
+  "偶": 57573,
+  "偿": 57541,
+  "兑": 57621,
+  "册": 57580,
+  "况": 57531,
+  "凤": 57609,
+  "刁": 57537,
+  "劝": 57590,
+  "匹": 57554,
+  "卸": 57568,
+  "厢": 57607,
+  "叉": 57577,
+  "吕": 57558,
+  "址": 57538,
+  "培": 57536,
+  "塘": 57605,
+  "够": 57587,
+  "央": 57546,
+  "姜": 57602,
+  "娟": 57601,
+  "娱": 57566,
+  "娶": 57542,
+  "婕": 57616,
+  "履": 57556,
+  "峡": 57603,
+  "崔": 57578,
+  "弃": 57595,
+  "弢": 57617,
+  "循": 57571,
+  "怖": 57560,
+  "怡": 57625,
+  "愁": 57608,
+  "披": 57526,
+  "担": 57593,
+  "摘": 57572,
+  "撑": 57592,
+  "擅": 57594,
+  "旦": 57549,
+  "旭": 57583,
+  "晰": 57618,
+  "朋": 57543,
+  "构": 57567,
+  "析": 57553,
+  "栋": 57575,
+  "橘": 57615,
+  "殊": 57591,
+  "毫": 57552,
+  "沟": 57596,
+  "泄": 57581,
+  "浅": 57623,
+  "济": 57570,
+  "涛": 57628,
+  "滚": 57539,
+  "滤": 57597,
+  "滨": 57545,
+  "灌": 57562,
+  "烦": 57532,
+  "烯": 57551,
+  "焕": 57557,
+  "皓": 57534,
+  "确": 57620,
+  "磊": 57547,
+  "绍": 57612,
+  "绕": 57600,
+  "综": 57613,
+  "缠": 57604,
+  "罚": 57563,
+  "翠": 57527,
+  "艳": 57550,
+  "芯": 57627,
+  "葛": 57569,
+  "蕾": 57574,
+  "螺": 57586,
+  "裕": 57624,
+  "裸": 57629,
+  "詹": 57529,
+  "训": 57589,
+  "询": 57599,
+  "诱": 57533,
+  "贤": 57606,
+  "赔": 57614,
+  "辆": 57535,
+  "辉": 57579,
+  "辐": 57588,
+  "辖": 57548,
+  "递": 57559,
+  "郑": 57626,
+  "郝": 57564,
+  "释": 57555,
+  "鑫": 57530,
+  "铭": 57544,
+  "链": 57611,
+  "际": 57540,
+  "陷": 57622,
+  "雇": 57582,
+  "颜": 57585,
+  "验": 57561,
+  "鸣": 57565,
+  "鼎": 57584,
+  "龚": 57576
+}

config.json

@@ -0,0 +1,23 @@
+{
+  "align_long_axis": true,
+  "architectures": [
+    "DonutModel"
+  ],
+  "decoder_layer": 4,
+  "encoder_layer": [
+    2,
+    2,
+    14,
+    2
+  ],
+  "input_size": [
+    2560,
+    1920
+  ],
+  "max_length": 1536,
+  "max_position_embeddings": 1536,
+  "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:d21e8b5e708168f4f9885d18f8bc95ad6950439e7ac518161828ff0b27b984e8
+size 1018458179

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_iitcdip>", "<s_synthdog>"]}

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"}