Hugging Face's logo

onnx-community
/
Dolphin-ONNX

Image-to-Text
Transformers.js
ONNX
vision-encoder-decoder
Model card Files
xet
Community
Xenova HF Staff commited on
Commit
2fcbd6e
·
verified ·
1 Parent(s): 5498cf1

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. config.json +193 -0
  2. generation_config.json +8 -0
  3. onnx/decoder_model_merged.onnx +3 -0
  4. onnx/decoder_model_merged_bnb4.onnx +3 -0
  5. onnx/decoder_model_merged_fp16.onnx +3 -0
  6. onnx/decoder_model_merged_int8.onnx +3 -0
  7. onnx/decoder_model_merged_q4.onnx +3 -0
  8. onnx/decoder_model_merged_q4f16.onnx +3 -0
  9. onnx/decoder_model_merged_quantized.onnx +3 -0
  10. onnx/decoder_model_merged_uint8.onnx +3 -0
  11. onnx/encoder_model.onnx +3 -0
  12. onnx/encoder_model_bnb4.onnx +3 -0
  13. onnx/encoder_model_fp16.onnx +3 -0
  14. onnx/encoder_model_int8.onnx +3 -0
  15. onnx/encoder_model_q4.onnx +3 -0
  16. onnx/encoder_model_q4f16.onnx +3 -0
  17. onnx/encoder_model_quantized.onnx +3 -0
  18. onnx/encoder_model_uint8.onnx +3 -0
  19. preprocessor_config.json +27 -0
  20. special_tokens_map.json +33 -0
  21. tokenizer.json +0 -0
  22. tokenizer_config.json +0 -0
config.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "ByteDance/Dolphin",
4
+ "architectures": [
5
+ "VisionEncoderDecoderModel"
6
+ ],
7
+ "decoder": {
8
+ "_attn_implementation_autoset": true,
9
+ "_name_or_path": "",
10
+ "activation_dropout": 0.0,
11
+ "activation_function": "gelu",
12
+ "add_cross_attention": true,
13
+ "add_final_layer_norm": true,
14
+ "architectures": null,
15
+ "attention_dropout": 0.0,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 0,
19
+ "chunk_size_feed_forward": 0,
20
+ "classifier_dropout": 0.0,
21
+ "cross_attention_hidden_size": null,
22
+ "d_model": 1024,
23
+ "decoder_attention_heads": 16,
24
+ "decoder_ffn_dim": 4096,
25
+ "decoder_layerdrop": 0.0,
26
+ "decoder_layers": 10,
27
+ "decoder_start_token_id": null,
28
+ "diversity_penalty": 0.0,
29
+ "do_sample": false,
30
+ "dropout": 0.1,
31
+ "early_stopping": false,
32
+ "encoder_attention_heads": 16,
33
+ "encoder_ffn_dim": 4096,
34
+ "encoder_layerdrop": 0.0,
35
+ "encoder_layers": 12,
36
+ "encoder_no_repeat_ngram_size": 0,
37
+ "eos_token_id": 2,
38
+ "exponential_decay_length_penalty": null,
39
+ "finetuning_task": null,
40
+ "forced_bos_token_id": null,
41
+ "forced_eos_token_id": 2,
42
+ "id2label": {
43
+ "0": "LABEL_0",
44
+ "1": "LABEL_1"
45
+ },
46
+ "init_std": 0.02,
47
+ "is_decoder": true,
48
+ "is_encoder_decoder": false,
49
+ "label2id": {
50
+ "LABEL_0": 0,
51
+ "LABEL_1": 1
52
+ },
53
+ "length_penalty": 1.0,
54
+ "max_length": 20,
55
+ "max_position_embeddings": 4096,
56
+ "min_length": 0,
57
+ "model_type": "mbart",
58
+ "no_repeat_ngram_size": 0,
59
+ "num_beam_groups": 1,
60
+ "num_beams": 1,
61
+ "num_hidden_layers": 12,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": 1,
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "return_dict": true,
73
+ "return_dict_in_generate": false,
74
+ "scale_embedding": true,
75
+ "sep_token_id": null,
76
+ "suppress_tokens": null,
77
+ "task_specific_params": null,
78
+ "temperature": 1.0,
79
+ "tf_legacy_loss": false,
80
+ "tie_encoder_decoder": false,
81
+ "tie_word_embeddings": false,
82
+ "tokenizer_class": null,
83
+ "top_k": 50,
84
+ "top_p": 1.0,
85
+ "torch_dtype": "float32",
86
+ "torchscript": false,
87
+ "typical_p": 1.0,
88
+ "use_bfloat16": false,
89
+ "use_cache": true,
90
+ "vocab_size": 73921
91
+ },
92
+ "encoder": {
93
+ "_attn_implementation_autoset": true,
94
+ "_name_or_path": "",
95
+ "add_cross_attention": false,
96
+ "architectures": null,
97
+ "attention_probs_dropout_prob": 0.0,
98
+ "bad_words_ids": null,
99
+ "begin_suppress_tokens": null,
100
+ "bos_token_id": null,
101
+ "chunk_size_feed_forward": 0,
102
+ "cross_attention_hidden_size": null,
103
+ "decoder_start_token_id": null,
104
+ "depths": [
105
+ 2,
106
+ 2,
107
+ 14,
108
+ 2
109
+ ],
110
+ "diversity_penalty": 0.0,
111
+ "do_sample": false,
112
+ "drop_path_rate": 0.1,
113
+ "early_stopping": false,
114
+ "embed_dim": 128,
115
+ "encoder_no_repeat_ngram_size": 0,
116
+ "eos_token_id": null,
117
+ "exponential_decay_length_penalty": null,
118
+ "finetuning_task": null,
119
+ "forced_bos_token_id": null,
120
+ "forced_eos_token_id": null,
121
+ "hidden_act": "gelu",
122
+ "hidden_dropout_prob": 0.0,
123
+ "hidden_size": 1024,
124
+ "id2label": {
125
+ "0": "LABEL_0",
126
+ "1": "LABEL_1"
127
+ },
128
+ "image_size": [
129
+ 896,
130
+ 896
131
+ ],
132
+ "initializer_range": 0.02,
133
+ "is_decoder": false,
134
+ "is_encoder_decoder": false,
135
+ "label2id": {
136
+ "LABEL_0": 0,
137
+ "LABEL_1": 1
138
+ },
139
+ "layer_norm_eps": 1e-05,
140
+ "length_penalty": 1.0,
141
+ "max_length": 20,
142
+ "min_length": 0,
143
+ "mlp_ratio": 4.0,
144
+ "model_type": "donut-swin",
145
+ "no_repeat_ngram_size": 0,
146
+ "num_beam_groups": 1,
147
+ "num_beams": 1,
148
+ "num_channels": 3,
149
+ "num_heads": [
150
+ 4,
151
+ 8,
152
+ 16,
153
+ 32
154
+ ],
155
+ "num_layers": 4,
156
+ "num_return_sequences": 1,
157
+ "output_attentions": false,
158
+ "output_hidden_states": false,
159
+ "output_scores": false,
160
+ "pad_token_id": null,
161
+ "patch_size": 4,
162
+ "prefix": null,
163
+ "problem_type": null,
164
+ "pruned_heads": {},
165
+ "qkv_bias": true,
166
+ "remove_invalid_values": false,
167
+ "repetition_penalty": 1.0,
168
+ "return_dict": true,
169
+ "return_dict_in_generate": false,
170
+ "sep_token_id": null,
171
+ "suppress_tokens": null,
172
+ "task_specific_params": null,
173
+ "temperature": 1.0,
174
+ "tf_legacy_loss": false,
175
+ "tie_encoder_decoder": false,
176
+ "tie_word_embeddings": true,
177
+ "tokenizer_class": null,
178
+ "top_k": 50,
179
+ "top_p": 1.0,
180
+ "torch_dtype": "float32",
181
+ "torchscript": false,
182
+ "typical_p": 1.0,
183
+ "use_absolute_embeddings": false,
184
+ "use_bfloat16": false,
185
+ "window_size": 7
186
+ },
187
+ "is_encoder_decoder": true,
188
+ "model_type": "vision-encoder-decoder",
189
+ "tie_word_embeddings": false,
190
+ "torch_dtype": "float32",
191
+ "transformers_version": "4.49.0",
192
+ "use_cache": true
193
+ }
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": "4.49.0"
8
+ }
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:518754d3078095cea8fd23460e0ae7572a980f32709b354a8f8c11b057eb80c7
3
+ size 1295164796
onnx/decoder_model_merged_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21bb29633eb14c8a2a9273865633bcfda0b11774c3fc874b35095e3a433e05e2
3
+ size 458273779
onnx/decoder_model_merged_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:862681699688f028c86daeaae2898a6c234bc070c7a1bfefb6df6c7fac50cd26
3
+ size 648064540
onnx/decoder_model_merged_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc120b3615fa6f62d5df2722a872cd6cff86caf71b9d4c259b2c2f8f84d55c5
3
+ size 325318348
onnx/decoder_model_merged_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da29a0b4cddcf5976d8a89d787c61e2c354fb7c122fb6b20ddcde01f96e01c2
3
+ size 473488937
onnx/decoder_model_merged_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b01689440f55f69ea00cd1114655c1214dbd428f95836dcdde3d98c127c287d9
3
+ size 298106507
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc120b3615fa6f62d5df2722a872cd6cff86caf71b9d4c259b2c2f8f84d55c5
3
+ size 325318348
onnx/decoder_model_merged_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff308c4662b8ea9639fded993fac79e4e3f109fc3a59d2a62e4835c2581899d
3
+ size 325318401
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:470032922ae5d66eb7fc6a991aad562d20d53011f118a836d279bd343ffe8da6
3
+ size 300639225
onnx/encoder_model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd71a622ff357ee7dbded97c96ef61dacc65b621a1b0be4f1a5aff3ff54ad6f
3
+ size 46542863
onnx/encoder_model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3981d71a70db460c03b7c02f3b8999cde4e0b23e89664b88acd3249f88111fed
3
+ size 151004659
onnx/encoder_model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:323793514ba451b03d7eb2a89a005750cf03fd8d7c72ad7bd3d44e799378b1b1
3
+ size 79011029
onnx/encoder_model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ed616bea6b39710ab8021e73125cb9e397b51eb76e0ea181eebccbc1e1a335e
3
+ size 51162176
onnx/encoder_model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f906ee092559d35fedd44e60089a5d8405a6d6fce02431ca70a0c3fff2f2e0e9
3
+ size 44756539
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667264d62a113b927b2022f7de0e7a089fef70ba7e2a513b685b6e7ddc79690
3
+ size 79011084
onnx/encoder_model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667264d62a113b927b2022f7de0e7a089fef70ba7e2a513b685b6e7ddc79690
3
+ size 79011084
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_align_long_axis": true,
3
+ "do_crop_margin": false,
4
+ "do_normalize": true,
5
+ "do_pad": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "do_thumbnail": true,
9
+ "image_mean": [
10
+ 0.485,
11
+ 0.456,
12
+ 0.406
13
+ ],
14
+ "image_processor_type": "DonutImageProcessor",
15
+ "image_std": [
16
+ 0.229,
17
+ 0.224,
18
+ 0.225
19
+ ],
20
+ "processor_class": "DonutProcessor",
21
+ "resample": 2,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "height": 896,
25
+ "width": 896
26
+ }
27
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ " <Answer/>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff