Hugging Face's logo

vukpetar
/
trocr-small-photomath

Image-Text-to-Text
Transformers
PyTorch
vision-encoder-decoder
Inference Endpoints
Model card Files Community
3
vukpetar commited on
Commit
b73e943
•
1 Parent(s): 43fc89b

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +169 -0
config.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/trocr-small-stage1",
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "decoder": {
8
+ "_name_or_path": "",
9
+ "activation_dropout": 0.0,
10
+ "activation_function": "relu",
11
+ "add_cross_attention": true,
12
+ "architectures": null,
13
+ "attention_dropout": 0.0,
14
+ "bad_words_ids": null,
15
+ "bos_token_id": 0,
16
+ "chunk_size_feed_forward": 0,
17
+ "classifier_dropout": 0.0,
18
+ "cross_attention_hidden_size": 384,
19
+ "d_model": 256,
20
+ "decoder_attention_heads": 8,
21
+ "decoder_ffn_dim": 1024,
22
+ "decoder_layerdrop": 0.0,
23
+ "decoder_layers": 6,
24
+ "decoder_start_token_id": 2,
25
+ "diversity_penalty": 0.0,
26
+ "do_sample": false,
27
+ "dropout": 0.1,
28
+ "early_stopping": false,
29
+ "encoder_no_repeat_ngram_size": 0,
30
+ "eos_token_id": 2,
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": 4,
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": true,
67
+ "sep_token_id": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": false,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "transformers_version": "4.15.0",
78
+ "use_bfloat16": false,
79
+ "use_cache": false,
80
+ "use_learned_position_embeddings": true,
81
+ "vocab_size": 64044
82
+ },
83
+ "decoder_start_token_id": 0,
84
+ "early_stopping": true,
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
+ "eos_token_id": null,
100
+ "finetuning_task": null,
101
+ "forced_bos_token_id": null,
102
+ "forced_eos_token_id": null,
103
+ "hidden_act": "gelu",
104
+ "hidden_dropout_prob": 0.0,
105
+ "hidden_size": 384,
106
+ "id2label": {
107
+ "0": "LABEL_0",
108
+ "1": "LABEL_1"
109
+ },
110
+ "image_size": 384,
111
+ "initializer_range": 0.02,
112
+ "intermediate_size": 1536,
113
+ "is_decoder": false,
114
+ "is_encoder_decoder": false,
115
+ "label2id": {
116
+ "LABEL_0": 0,
117
+ "LABEL_1": 1
118
+ },
119
+ "layer_norm_eps": 1e-12,
120
+ "length_penalty": 1.0,
121
+ "max_length": 20,
122
+ "min_length": 0,
123
+ "model_type": "deit",
124
+ "no_repeat_ngram_size": 0,
125
+ "num_attention_heads": 6,
126
+ "num_beam_groups": 1,
127
+ "num_beams": 4,
128
+ "num_channels": 3,
129
+ "num_hidden_layers": 12,
130
+ "num_return_sequences": 1,
131
+ "output_attentions": false,
132
+ "output_hidden_states": false,
133
+ "output_scores": false,
134
+ "pad_token_id": null,
135
+ "patch_size": 16,
136
+ "prefix": null,
137
+ "problem_type": null,
138
+ "pruned_heads": {},
139
+ "qkv_bias": true,
140
+ "remove_invalid_values": false,
141
+ "repetition_penalty": 1.0,
142
+ "return_dict": true,
143
+ "return_dict_in_generate": false,
144
+ "sep_token_id": null,
145
+ "task_specific_params": null,
146
+ "temperature": 1.0,
147
+ "tie_encoder_decoder": false,
148
+ "tie_word_embeddings": true,
149
+ "tokenizer_class": null,
150
+ "top_k": 50,
151
+ "top_p": 1.0,
152
+ "torch_dtype": null,
153
+ "torchscript": false,
154
+ "transformers_version": "4.15.0",
155
+ "use_bfloat16": false
156
+ },
157
+ "eos_token_id": 2,
158
+ "is_encoder_decoder": true,
159
+ "length_penalty": 2.0,
160
+ "max_length": 64,
161
+ "model_type": "vision-encoder-decoder",
162
+ "no_repeat_ngram_size": 3,
163
+ "num_beams": 4,
164
+ "pad_token_id": 1,
165
+ "tie_word_embeddings": false,
166
+ "torch_dtype": "float32",
167
+ "transformers_version": null,
168
+ "vocab_size": 64044
169
+ }