Hugging Face's logo

microsoft
/
trocr-base-str

Image-to-Text Transformers PyTorch vision-encoder-decoder trocr Inference Endpoints
Model card Files Community
1
liminghao1630 commited on
Commit
44bfd29
•
1 Parent(s): ecbacb2

add model

Browse files
Files changed (2) hide show
  1. config.json +167 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "trocr-base-str",
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
+ "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": 768,
18
+ "d_model": 1024,
19
+ "decoder_attention_heads": 16,
20
+ "decoder_ffn_dim": 4096,
21
+ "decoder_layerdrop": 0.0,
22
+ "decoder_layers": 12,
23
+ "decoder_start_token_id": 2,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "dropout": 0.1,
27
+ "early_stopping": false,
28
+ "encoder_no_repeat_ngram_size": 0,
29
+ "eos_token_id": 2,
30
+ "exponential_decay_length_penalty": null,
31
+ "finetuning_task": null,
32
+ "forced_bos_token_id": null,
33
+ "forced_eos_token_id": null,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "init_std": 0.02,
39
+ "is_decoder": true,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "layernorm_embedding": true,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 512,
49
+ "min_length": 0,
50
+ "model_type": "trocr",
51
+ "no_repeat_ngram_size": 0,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_return_sequences": 1,
55
+ "output_attentions": false,
56
+ "output_hidden_states": false,
57
+ "output_scores": false,
58
+ "pad_token_id": 1,
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "scale_embedding": false,
67
+ "sep_token_id": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tf_legacy_loss": false,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "transformers_version": "4.21.3",
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "use_cache": false,
82
+ "use_learned_position_embeddings": true,
83
+ "vocab_size": 50265
84
+ },
85
+ "encoder": {
86
+ "_name_or_path": "",
87
+ "add_cross_attention": false,
88
+ "architectures": null,
89
+ "attention_probs_dropout_prob": 0.0,
90
+ "bad_words_ids": null,
91
+ "bos_token_id": null,
92
+ "chunk_size_feed_forward": 0,
93
+ "cross_attention_hidden_size": null,
94
+ "decoder_start_token_id": null,
95
+ "diversity_penalty": 0.0,
96
+ "do_sample": false,
97
+ "early_stopping": false,
98
+ "encoder_no_repeat_ngram_size": 0,
99
+ "encoder_stride": 16,
100
+ "eos_token_id": null,
101
+ "exponential_decay_length_penalty": null,
102
+ "finetuning_task": null,
103
+ "forced_bos_token_id": null,
104
+ "forced_eos_token_id": null,
105
+ "hidden_act": "gelu",
106
+ "hidden_dropout_prob": 0.0,
107
+ "hidden_size": 768,
108
+ "id2label": {
109
+ "0": "LABEL_0",
110
+ "1": "LABEL_1"
111
+ },
112
+ "image_size": 384,
113
+ "initializer_range": 0.02,
114
+ "intermediate_size": 3072,
115
+ "is_decoder": false,
116
+ "is_encoder_decoder": false,
117
+ "label2id": {
118
+ "LABEL_0": 0,
119
+ "LABEL_1": 1
120
+ },
121
+ "layer_norm_eps": 1e-12,
122
+ "length_penalty": 1.0,
123
+ "max_length": 20,
124
+ "min_length": 0,
125
+ "model_type": "vit",
126
+ "no_repeat_ngram_size": 0,
127
+ "num_attention_heads": 12,
128
+ "num_beam_groups": 1,
129
+ "num_beams": 1,
130
+ "num_channels": 3,
131
+ "num_hidden_layers": 12,
132
+ "num_return_sequences": 1,
133
+ "output_attentions": false,
134
+ "output_hidden_states": false,
135
+ "output_scores": false,
136
+ "pad_token_id": null,
137
+ "patch_size": 16,
138
+ "prefix": null,
139
+ "problem_type": null,
140
+ "pruned_heads": {},
141
+ "qkv_bias": false,
142
+ "remove_invalid_values": false,
143
+ "repetition_penalty": 1.0,
144
+ "return_dict": true,
145
+ "return_dict_in_generate": false,
146
+ "sep_token_id": null,
147
+ "task_specific_params": null,
148
+ "temperature": 1.0,
149
+ "tf_legacy_loss": false,
150
+ "tie_encoder_decoder": false,
151
+ "tie_word_embeddings": true,
152
+ "tokenizer_class": null,
153
+ "top_k": 50,
154
+ "top_p": 1.0,
155
+ "torch_dtype": null,
156
+ "torchscript": false,
157
+ "transformers_version": "4.21.3",
158
+ "typical_p": 1.0,
159
+ "use_bfloat16": false
160
+ },
161
+ "eos_token_id": 2,
162
+ "is_encoder_decoder": true,
163
+ "model_type": "vision-encoder-decoder",
164
+ "tie_word_embeddings": false,
165
+ "torch_dtype": "float32",
166
+ "transformers_version": null
167
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaff179cd469b751f3afa999ca3ed0ab178373e8b46ad060342cabd8cc277085
3
+ size 1335844033