initial commit
Browse files- added_tokens.json +1 -0
- config.json +24 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "naver-clova-ix/donut-base",
|
3 |
+
"align_long_axis": false,
|
4 |
+
"architectures": [
|
5 |
+
"DonutModel"
|
6 |
+
],
|
7 |
+
"decoder_layer": 4,
|
8 |
+
"encoder_layer": [
|
9 |
+
2,
|
10 |
+
2,
|
11 |
+
14,
|
12 |
+
2
|
13 |
+
],
|
14 |
+
"input_size": [
|
15 |
+
2560,
|
16 |
+
1920
|
17 |
+
],
|
18 |
+
"max_length": 128,
|
19 |
+
"max_position_embeddings": 128,
|
20 |
+
"model_type": "donut",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.11.3",
|
23 |
+
"window_size": 10
|
24 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c7b40074bc43cde8ec5097a3b1acd0c0e83fa506478739af34c8722cadbc0e8
|
3 |
+
size 1012719683
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
|
3 |
+
size 1296245
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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"}
|