nielsr HF staff commited on
Commit
12d4c6b
1 Parent(s): 1d40bcc

Add HuggingFace files (#1)

Browse files

- Add files (042e6831d852424165bfb568c2196dd16520fe99)

.gitignore ADDED
@@ -0,0 +1 @@
 
1
+ .DS_Store
README.md DELETED
@@ -1,3 +0,0 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
added_tokens.json CHANGED
@@ -1 +1,24 @@
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}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_class>": 57523,
3
+ "<advertisement/>": 57524,
4
+ "<budget/>": 57525,
5
+ "<email/>": 57526,
6
+ "<file_folder/>": 57527,
7
+ "<form/>": 57528,
8
+ "<handwritten/>": 57529,
9
+ "<invoice/>": 57530,
10
+ "<letter/>": 57531,
11
+ "<memo/>": 57532,
12
+ "<news_article/>": 57533,
13
+ "<presentation/>": 57534,
14
+ "<questionnaire/>": 57535,
15
+ "<resume/>": 57536,
16
+ "<s_class>": 57537,
17
+ "<s_iitcdip>": 57538,
18
+ "<s_rvlcdip>": 57539,
19
+ "<s_synthdog>": 57540,
20
+ "<scientific_publication/>": 57541,
21
+ "<scientific_report/>": 57542,
22
+ "<sep/>": 57522,
23
+ "<specification/>": 57543
24
+ }
config.json CHANGED
@@ -1,24 +1,187 @@
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": 8,
19
- "max_position_embeddings": 8,
20
- "model_type": "donut",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "torch_dtype": "float32",
22
- "transformers_version": "4.11.3",
23
- "window_size": 10
24
  }
1
  {
 
 
2
  "architectures": [
3
+ "VisionEncoderDecoderModel"
4
  ],
5
+ "decoder": {
6
+ "_name_or_path": "",
7
+ "activation_dropout": 0.0,
8
+ "activation_function": "gelu",
9
+ "add_cross_attention": true,
10
+ "add_final_layer_norm": true,
11
+ "architectures": null,
12
+ "attention_dropout": 0.0,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 0,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": 0.0,
17
+ "cross_attention_hidden_size": null,
18
+ "d_model": 1024,
19
+ "decoder_attention_heads": 16,
20
+ "decoder_ffn_dim": 4096,
21
+ "decoder_layerdrop": 0.0,
22
+ "decoder_layers": 4,
23
+ "decoder_start_token_id": null,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "dropout": 0.1,
27
+ "early_stopping": false,
28
+ "encoder_attention_heads": 16,
29
+ "encoder_ffn_dim": 4096,
30
+ "encoder_layerdrop": 0.0,
31
+ "encoder_layers": 12,
32
+ "encoder_no_repeat_ngram_size": 0,
33
+ "eos_token_id": 2,
34
+ "exponential_decay_length_penalty": null,
35
+ "finetuning_task": null,
36
+ "forced_bos_token_id": null,
37
+ "forced_eos_token_id": 2,
38
+ "id2label": {
39
+ "0": "LABEL_0",
40
+ "1": "LABEL_1"
41
+ },
42
+ "init_std": 0.02,
43
+ "is_decoder": true,
44
+ "is_encoder_decoder": false,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1
48
+ },
49
+ "length_penalty": 1.0,
50
+ "max_length": 20,
51
+ "max_position_embeddings": 8,
52
+ "min_length": 0,
53
+ "model_type": "mbart",
54
+ "no_repeat_ngram_size": 0,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 12,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 1,
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "pruned_heads": {},
66
+ "remove_invalid_values": false,
67
+ "repetition_penalty": 1.0,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "scale_embedding": true,
71
+ "sep_token_id": null,
72
+ "task_specific_params": null,
73
+ "temperature": 1.0,
74
+ "tf_legacy_loss": false,
75
+ "tie_encoder_decoder": false,
76
+ "tie_word_embeddings": true,
77
+ "tokenizer_class": null,
78
+ "top_k": 50,
79
+ "top_p": 1.0,
80
+ "torch_dtype": null,
81
+ "torchscript": false,
82
+ "transformers_version": "4.22.0.dev0",
83
+ "typical_p": 1.0,
84
+ "use_bfloat16": false,
85
+ "use_cache": true,
86
+ "vocab_size": 57544
87
+ },
88
+ "encoder": {
89
+ "_name_or_path": "",
90
+ "add_cross_attention": false,
91
+ "architectures": null,
92
+ "attention_probs_dropout_prob": 0.0,
93
+ "bad_words_ids": null,
94
+ "bos_token_id": null,
95
+ "chunk_size_feed_forward": 0,
96
+ "cross_attention_hidden_size": null,
97
+ "decoder_start_token_id": null,
98
+ "depths": [
99
+ 2,
100
+ 2,
101
+ 14,
102
+ 2
103
+ ],
104
+ "diversity_penalty": 0.0,
105
+ "do_sample": false,
106
+ "drop_path_rate": 0.1,
107
+ "early_stopping": false,
108
+ "embed_dim": 128,
109
+ "encoder_no_repeat_ngram_size": 0,
110
+ "eos_token_id": null,
111
+ "exponential_decay_length_penalty": null,
112
+ "finetuning_task": null,
113
+ "forced_bos_token_id": null,
114
+ "forced_eos_token_id": null,
115
+ "hidden_act": "gelu",
116
+ "hidden_dropout_prob": 0.0,
117
+ "hidden_size": 1024,
118
+ "id2label": {
119
+ "0": "LABEL_0",
120
+ "1": "LABEL_1"
121
+ },
122
+ "image_size": [
123
+ 2560,
124
+ 1920
125
+ ],
126
+ "initializer_range": 0.02,
127
+ "is_decoder": false,
128
+ "is_encoder_decoder": false,
129
+ "label2id": {
130
+ "LABEL_0": 0,
131
+ "LABEL_1": 1
132
+ },
133
+ "layer_norm_eps": 1e-05,
134
+ "length_penalty": 1.0,
135
+ "max_length": 20,
136
+ "min_length": 0,
137
+ "mlp_ratio": 4.0,
138
+ "model_type": "donut-swin",
139
+ "no_repeat_ngram_size": 0,
140
+ "num_beam_groups": 1,
141
+ "num_beams": 1,
142
+ "num_channels": 3,
143
+ "num_heads": [
144
+ 4,
145
+ 8,
146
+ 16,
147
+ 32
148
+ ],
149
+ "num_layers": 4,
150
+ "num_return_sequences": 1,
151
+ "output_attentions": false,
152
+ "output_hidden_states": false,
153
+ "output_scores": false,
154
+ "pad_token_id": null,
155
+ "patch_size": 4,
156
+ "path_norm": true,
157
+ "prefix": null,
158
+ "problem_type": null,
159
+ "pruned_heads": {},
160
+ "qkv_bias": true,
161
+ "remove_invalid_values": false,
162
+ "repetition_penalty": 1.0,
163
+ "return_dict": true,
164
+ "return_dict_in_generate": false,
165
+ "sep_token_id": null,
166
+ "task_specific_params": null,
167
+ "temperature": 1.0,
168
+ "tf_legacy_loss": false,
169
+ "tie_encoder_decoder": false,
170
+ "tie_word_embeddings": true,
171
+ "tokenizer_class": null,
172
+ "top_k": 50,
173
+ "top_p": 1.0,
174
+ "torch_dtype": null,
175
+ "torchscript": false,
176
+ "transformers_version": "4.22.0.dev0",
177
+ "typical_p": 1.0,
178
+ "use_absolute_embeddings": false,
179
+ "use_bfloat16": false,
180
+ "window_size": 10
181
+ },
182
+ "is_encoder_decoder": true,
183
+ "model_type": "vision-encoder-decoder",
184
+ "tie_word_embeddings": false,
185
  "torch_dtype": "float32",
186
+ "transformers_version": null
 
187
  }
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_align_long_axis": false,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_resize": true,
6
+ "do_thumbnail": true,
7
+ "feature_extractor_type": "DonutFeatureExtractor",
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "processor_class": "DonutProcessor",
19
+ "resample": 2,
20
+ "size": [
21
+ 1920,
22
+ 2560
23
+ ]
24
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c017dfaaa742078b13267bc89a880f76825af51eeec916076b013f8b6e6956c3
3
- size 1012277315
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0e37d027ce4efbb6a868c6d64622301f67f045e31c92b0b86fd085b41146176
3
+ size 802987835
sentencepiece.bpe.model CHANGED
File without changes
special_tokens_map.json CHANGED
@@ -1 +1,38 @@
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/>"]}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "</s_class>",
4
+ "<advertisement/>",
5
+ "<budget/>",
6
+ "<email/>",
7
+ "<file_folder/>",
8
+ "<form/>",
9
+ "<handwritten/>",
10
+ "<invoice/>",
11
+ "<letter/>",
12
+ "<memo/>",
13
+ "<news_article/>",
14
+ "<presentation/>",
15
+ "<questionnaire/>",
16
+ "<resume/>",
17
+ "<s_class>",
18
+ "<s_iitcdip>",
19
+ "<s_rvlcdip>",
20
+ "<s_synthdog>",
21
+ "<scientific_publication/>",
22
+ "<scientific_report/>",
23
+ "<specification/>"
24
+ ],
25
+ "bos_token": "<s>",
26
+ "cls_token": "<s>",
27
+ "eos_token": "</s>",
28
+ "mask_token": {
29
+ "content": "<mask>",
30
+ "lstrip": true,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "pad_token": "<pad>",
36
+ "sep_token": "</s>",
37
+ "unk_token": "<unk>"
38
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json CHANGED
@@ -1 +1,22 @@
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"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "from_slow": true,
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "name_or_path": "naver-clova-ix/donut-base-finetuned-rvlcdip",
15
+ "pad_token": "<pad>",
16
+ "processor_class": "DonutProcessor",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "unk_token": "<unk>"
22
+ }