Xenova HF staff commited on
Commit
d9868f6
1 Parent(s): 0c633a8

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_cashprice>": 57549,
3
+ "</s_changeprice>": 57551,
4
+ "</s_cnt>": 57529,
5
+ "</s_creditcardprice>": 57563,
6
+ "</s_discount_price>": 57557,
7
+ "</s_discountprice>": 57567,
8
+ "</s_emoneyprice>": 57569,
9
+ "</s_etc>": 57541,
10
+ "</s_itemsubtotal>": 57577,
11
+ "</s_menu>": 57525,
12
+ "</s_menuqty_cnt>": 57555,
13
+ "</s_menutype_cnt>": 57553,
14
+ "</s_nm>": 57527,
15
+ "</s_num>": 57565,
16
+ "</s_othersvc_price>": 57573,
17
+ "</s_price>": 57531,
18
+ "</s_service_price>": 57537,
19
+ "</s_sub>": 57547,
20
+ "</s_sub_total>": 57533,
21
+ "</s_subtotal_price>": 57535,
22
+ "</s_tax_price>": 57539,
23
+ "</s_total>": 57543,
24
+ "</s_total_etc>": 57561,
25
+ "</s_total_price>": 57545,
26
+ "</s_unitprice>": 57559,
27
+ "</s_vatyn>": 57575,
28
+ "</s_void_menu>": 57571,
29
+ "<s_cashprice>": 57550,
30
+ "<s_changeprice>": 57552,
31
+ "<s_cnt>": 57530,
32
+ "<s_cord-v2>": 57579,
33
+ "<s_creditcardprice>": 57564,
34
+ "<s_discount_price>": 57558,
35
+ "<s_discountprice>": 57568,
36
+ "<s_emoneyprice>": 57570,
37
+ "<s_etc>": 57542,
38
+ "<s_iitcdip>": 57523,
39
+ "<s_itemsubtotal>": 57578,
40
+ "<s_menu>": 57526,
41
+ "<s_menuqty_cnt>": 57556,
42
+ "<s_menutype_cnt>": 57554,
43
+ "<s_nm>": 57528,
44
+ "<s_num>": 57566,
45
+ "<s_othersvc_price>": 57574,
46
+ "<s_price>": 57532,
47
+ "<s_service_price>": 57538,
48
+ "<s_sub>": 57548,
49
+ "<s_sub_total>": 57534,
50
+ "<s_subtotal_price>": 57536,
51
+ "<s_synthdog>": 57524,
52
+ "<s_tax_price>": 57540,
53
+ "<s_total>": 57544,
54
+ "<s_total_etc>": 57562,
55
+ "<s_total_price>": 57546,
56
+ "<s_unitprice>": 57560,
57
+ "<s_vatyn>": 57576,
58
+ "<s_void_menu>": 57572,
59
+ "<sep/>": 57522
60
+ }
config.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "naver-clova-ix/donut-base-finetuned-cord-v2",
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "",
8
+ "activation_dropout": 0.0,
9
+ "activation_function": "gelu",
10
+ "add_cross_attention": true,
11
+ "add_final_layer_norm": true,
12
+ "architectures": null,
13
+ "attention_dropout": 0.0,
14
+ "bad_words_ids": null,
15
+ "begin_suppress_tokens": null,
16
+ "bos_token_id": 0,
17
+ "chunk_size_feed_forward": 0,
18
+ "classifier_dropout": 0.0,
19
+ "cross_attention_hidden_size": null,
20
+ "d_model": 1024,
21
+ "decoder_attention_heads": 16,
22
+ "decoder_ffn_dim": 4096,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 4,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "dropout": 0.1,
29
+ "early_stopping": false,
30
+ "encoder_attention_heads": 16,
31
+ "encoder_ffn_dim": 4096,
32
+ "encoder_layerdrop": 0.0,
33
+ "encoder_layers": 12,
34
+ "encoder_no_repeat_ngram_size": 0,
35
+ "eos_token_id": 2,
36
+ "exponential_decay_length_penalty": null,
37
+ "finetuning_task": null,
38
+ "forced_bos_token_id": null,
39
+ "forced_eos_token_id": 2,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1"
43
+ },
44
+ "init_std": 0.02,
45
+ "is_decoder": true,
46
+ "is_encoder_decoder": false,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
+ "length_penalty": 1.0,
52
+ "max_length": 20,
53
+ "max_position_embeddings": 768,
54
+ "min_length": 0,
55
+ "model_type": "mbart",
56
+ "no_repeat_ngram_size": 0,
57
+ "num_beam_groups": 1,
58
+ "num_beams": 1,
59
+ "num_hidden_layers": 12,
60
+ "num_return_sequences": 1,
61
+ "output_attentions": false,
62
+ "output_hidden_states": false,
63
+ "output_scores": false,
64
+ "pad_token_id": 1,
65
+ "prefix": null,
66
+ "problem_type": null,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "scale_embedding": true,
73
+ "sep_token_id": null,
74
+ "suppress_tokens": null,
75
+ "task_specific_params": null,
76
+ "temperature": 1.0,
77
+ "tf_legacy_loss": false,
78
+ "tie_encoder_decoder": false,
79
+ "tie_word_embeddings": true,
80
+ "tokenizer_class": null,
81
+ "top_k": 50,
82
+ "top_p": 1.0,
83
+ "torch_dtype": null,
84
+ "torchscript": false,
85
+ "typical_p": 1.0,
86
+ "use_bfloat16": false,
87
+ "use_cache": true,
88
+ "vocab_size": 57580
89
+ },
90
+ "encoder": {
91
+ "_name_or_path": "",
92
+ "add_cross_attention": false,
93
+ "architectures": null,
94
+ "attention_probs_dropout_prob": 0.0,
95
+ "bad_words_ids": null,
96
+ "begin_suppress_tokens": null,
97
+ "bos_token_id": null,
98
+ "chunk_size_feed_forward": 0,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "depths": [
102
+ 2,
103
+ 2,
104
+ 14,
105
+ 2
106
+ ],
107
+ "diversity_penalty": 0.0,
108
+ "do_sample": false,
109
+ "drop_path_rate": 0.1,
110
+ "early_stopping": false,
111
+ "embed_dim": 128,
112
+ "encoder_no_repeat_ngram_size": 0,
113
+ "eos_token_id": null,
114
+ "exponential_decay_length_penalty": null,
115
+ "finetuning_task": null,
116
+ "forced_bos_token_id": null,
117
+ "forced_eos_token_id": null,
118
+ "hidden_act": "gelu",
119
+ "hidden_dropout_prob": 0.0,
120
+ "hidden_size": 1024,
121
+ "id2label": {
122
+ "0": "LABEL_0",
123
+ "1": "LABEL_1"
124
+ },
125
+ "image_size": [
126
+ 1280,
127
+ 960
128
+ ],
129
+ "initializer_range": 0.02,
130
+ "is_decoder": false,
131
+ "is_encoder_decoder": false,
132
+ "label2id": {
133
+ "LABEL_0": 0,
134
+ "LABEL_1": 1
135
+ },
136
+ "layer_norm_eps": 1e-05,
137
+ "length_penalty": 1.0,
138
+ "max_length": 20,
139
+ "min_length": 0,
140
+ "mlp_ratio": 4.0,
141
+ "model_type": "donut-swin",
142
+ "no_repeat_ngram_size": 0,
143
+ "num_beam_groups": 1,
144
+ "num_beams": 1,
145
+ "num_channels": 3,
146
+ "num_heads": [
147
+ 4,
148
+ 8,
149
+ 16,
150
+ 32
151
+ ],
152
+ "num_layers": 4,
153
+ "num_return_sequences": 1,
154
+ "output_attentions": false,
155
+ "output_hidden_states": false,
156
+ "output_scores": false,
157
+ "pad_token_id": null,
158
+ "patch_size": 4,
159
+ "path_norm": true,
160
+ "prefix": null,
161
+ "problem_type": null,
162
+ "pruned_heads": {},
163
+ "qkv_bias": true,
164
+ "remove_invalid_values": false,
165
+ "repetition_penalty": 1.0,
166
+ "return_dict": true,
167
+ "return_dict_in_generate": false,
168
+ "sep_token_id": null,
169
+ "suppress_tokens": null,
170
+ "task_specific_params": null,
171
+ "temperature": 1.0,
172
+ "tf_legacy_loss": false,
173
+ "tie_encoder_decoder": false,
174
+ "tie_word_embeddings": true,
175
+ "tokenizer_class": null,
176
+ "top_k": 50,
177
+ "top_p": 1.0,
178
+ "torch_dtype": null,
179
+ "torchscript": false,
180
+ "typical_p": 1.0,
181
+ "use_absolute_embeddings": false,
182
+ "use_bfloat16": false,
183
+ "window_size": 10
184
+ },
185
+ "is_encoder_decoder": true,
186
+ "model_type": "vision-encoder-decoder",
187
+ "tie_word_embeddings": false,
188
+ "transformers_version": "4.33.0.dev0"
189
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.33.0.dev0"
8
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69c259b764d7af48bf4b5d0bd980a4e077faaecea989dcadcf6cf452fe2f1c52
3
+ size 507954282
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f9c357965ba8f3ab4e38af9cc48ab537c3cba22939ed6d7d0b1db0245d6db03
3
+ size 508113471
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f8f5a405f655aa3934a19e6e7a9d6bd81245bd002000fcc986414b95608ffa
3
+ size 128006964
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d35f3c11161319a9b5f272bb06010b78cb69147eedb92e7bed71357c407959dc
3
+ size 127755485
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b08f7f185233b349d3b3d9bf65d6f5a1aa543e0d24059533daf15608bf0dccb
3
+ size 474335740
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1597ac51facb91a854fa95e1a9d06922da5c6fd64a82d8ca383b43552aadc4c2
3
+ size 119242507
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ad32201f8eb333ea289a6029dec2cf2dd7fbfbea517da53f042b4be5723a85
3
+ size 311503397
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26432a04e1f74ff02875eaacb2f1ce6d7100a5747d0243a6c04d6f894893b612
3
+ size 91383413
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_align_long_axis": false,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "do_thumbnail": true,
8
+ "feature_extractor_type": "DonutFeatureExtractor",
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_processor_type": "DonutFeatureExtractor",
15
+ "image_std": [
16
+ 0.5,
17
+ 0.5,
18
+ 0.5
19
+ ],
20
+ "processor_class": "DonutProcessor",
21
+ "resample": 2,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "height": 1280,
25
+ "width": 960
26
+ }
27
+ }
quantize_config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Gather",
8
+ "Equal",
9
+ "Mul",
10
+ "Concat",
11
+ "Cast",
12
+ "Add",
13
+ "MatMul",
14
+ "Transpose",
15
+ "Shape",
16
+ "Where",
17
+ "Pow",
18
+ "Expand",
19
+ "ReduceMean",
20
+ "Div",
21
+ "Erf",
22
+ "Squeeze",
23
+ "Softmax",
24
+ "Less",
25
+ "Range",
26
+ "Sub",
27
+ "Sqrt",
28
+ "Slice",
29
+ "Constant",
30
+ "Reshape",
31
+ "ConstantOfShape",
32
+ "Unsqueeze"
33
+ ],
34
+ "weight_type": "QInt8"
35
+ },
36
+ "encoder_model": {
37
+ "op_types": [
38
+ "Gather",
39
+ "Equal",
40
+ "Mul",
41
+ "Concat",
42
+ "ScatterND",
43
+ "Mod",
44
+ "Add",
45
+ "Transpose",
46
+ "Cast",
47
+ "MatMul",
48
+ "Shape",
49
+ "Where",
50
+ "Pow",
51
+ "Erf",
52
+ "ReduceMean",
53
+ "Div",
54
+ "Expand",
55
+ "Pad",
56
+ "Conv",
57
+ "Softmax",
58
+ "Range",
59
+ "Sub",
60
+ "Sqrt",
61
+ "Slice",
62
+ "Constant",
63
+ "Reshape",
64
+ "ConstantOfShape",
65
+ "Not",
66
+ "Unsqueeze"
67
+ ],
68
+ "weight_type": "QUInt8"
69
+ },
70
+ "decoder_model_merged": {
71
+ "op_types": [
72
+ "Gather",
73
+ "Equal",
74
+ "Mul",
75
+ "Concat",
76
+ "Cast",
77
+ "Add",
78
+ "MatMul",
79
+ "Transpose",
80
+ "Shape",
81
+ "Where",
82
+ "Pow",
83
+ "Expand",
84
+ "ReduceMean",
85
+ "Div",
86
+ "Erf",
87
+ "Squeeze",
88
+ "Softmax",
89
+ "Less",
90
+ "Range",
91
+ "Sub",
92
+ "Sqrt",
93
+ "Slice",
94
+ "Constant",
95
+ "Reshape",
96
+ "If",
97
+ "ConstantOfShape",
98
+ "Unsqueeze"
99
+ ],
100
+ "weight_type": "QInt8"
101
+ },
102
+ "decoder_with_past_model": {
103
+ "op_types": [
104
+ "Gather",
105
+ "Equal",
106
+ "Mul",
107
+ "Concat",
108
+ "Add",
109
+ "Cast",
110
+ "MatMul",
111
+ "Transpose",
112
+ "Shape",
113
+ "Where",
114
+ "Pow",
115
+ "Expand",
116
+ "ReduceMean",
117
+ "Div",
118
+ "Erf",
119
+ "Softmax",
120
+ "Range",
121
+ "Sub",
122
+ "Sqrt",
123
+ "Constant",
124
+ "Reshape",
125
+ "ConstantOfShape",
126
+ "Unsqueeze"
127
+ ],
128
+ "weight_type": "QInt8"
129
+ }
130
+ }
131
+ }
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 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_cord-v2>"
4
+ ],
5
+ "bos_token": "<s>",
6
+ "cls_token": "<s>",
7
+ "eos_token": "</s>",
8
+ "mask_token": {
9
+ "content": "<mask>",
10
+ "lstrip": true,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "unk_token": "<unk>"
18
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 1000000000000000019884624838656,
15
+ "pad_token": "<pad>",
16
+ "processor_class": "DonutProcessor",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "tokenizer_class": "XLMRobertaTokenizer",
20
+ "unk_token": "<unk>"
21
+ }