Dawars commited on
Commit
1e0bc63
1 Parent(s): 882612d

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +188 -0
config.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/content/drive/MyDrive/exp_ocr_model/checkpoint-3000",
4
+ "architectures": [
5
+ "VisionEncoderDecoderModel"
6
+ ],
7
+ "decoder": {
8
+ "_name_or_path": "xlm-roberta-base",
9
+ "add_cross_attention": true,
10
+ "architectures": [
11
+ "XLMRobertaForMaskedLM"
12
+ ],
13
+ "attention_probs_dropout_prob": 0.1,
14
+ "bad_words_ids": null,
15
+ "begin_suppress_tokens": null,
16
+ "bos_token_id": 0,
17
+ "chunk_size_feed_forward": 0,
18
+ "classifier_dropout": null,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 2,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "hidden_act": "gelu",
31
+ "hidden_dropout_prob": 0.1,
32
+ "hidden_size": 768,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "is_decoder": true,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 514,
49
+ "min_length": 0,
50
+ "model_type": "xlm-roberta",
51
+ "no_repeat_ngram_size": 0,
52
+ "num_attention_heads": 12,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_hidden_layers": 12,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_past": true,
60
+ "output_scores": false,
61
+ "pad_token_id": 1,
62
+ "position_embedding_type": "absolute",
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
+ "sep_token_id": null,
71
+ "suppress_tokens": 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": "4.25.1",
83
+ "type_vocab_size": 1,
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "use_cache": true,
87
+ "vocab_size": 250002
88
+ },
89
+ "decoder_start_token_id": 0,
90
+ "early_stopping": true,
91
+ "encoder": {
92
+ "_name_or_path": "facebook/vit-mae-large",
93
+ "add_cross_attention": false,
94
+ "architectures": [
95
+ "ViTMAEForPreTraining"
96
+ ],
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_hidden_size": 512,
104
+ "decoder_intermediate_size": 2048,
105
+ "decoder_num_attention_heads": 16,
106
+ "decoder_num_hidden_layers": 8,
107
+ "decoder_start_token_id": null,
108
+ "diversity_penalty": 0.0,
109
+ "do_sample": false,
110
+ "early_stopping": false,
111
+ "encoder_no_repeat_ngram_size": 0,
112
+ "eos_token_id": null,
113
+ "exponential_decay_length_penalty": null,
114
+ "finetuning_task": null,
115
+ "forced_bos_token_id": null,
116
+ "forced_eos_token_id": null,
117
+ "hidden_act": "gelu",
118
+ "hidden_dropout_prob": 0.0,
119
+ "hidden_size": 1024,
120
+ "id2label": {
121
+ "0": "LABEL_0",
122
+ "1": "LABEL_1"
123
+ },
124
+ "image_size": 224,
125
+ "initializer_range": 0.02,
126
+ "intermediate_size": 4096,
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-12,
134
+ "length_penalty": 1.0,
135
+ "mask_ratio": 0.75,
136
+ "max_length": 20,
137
+ "min_length": 0,
138
+ "model_type": "vit_mae",
139
+ "no_repeat_ngram_size": 0,
140
+ "norm_pix_loss": false,
141
+ "num_attention_heads": 16,
142
+ "num_beam_groups": 1,
143
+ "num_beams": 1,
144
+ "num_channels": 3,
145
+ "num_hidden_layers": 24,
146
+ "num_return_sequences": 1,
147
+ "output_attentions": false,
148
+ "output_hidden_states": false,
149
+ "output_scores": false,
150
+ "pad_token_id": null,
151
+ "patch_size": 16,
152
+ "prefix": null,
153
+ "problem_type": null,
154
+ "pruned_heads": {},
155
+ "qkv_bias": true,
156
+ "remove_invalid_values": false,
157
+ "repetition_penalty": 1.0,
158
+ "return_dict": true,
159
+ "return_dict_in_generate": false,
160
+ "sep_token_id": null,
161
+ "suppress_tokens": null,
162
+ "task_specific_params": null,
163
+ "temperature": 1.0,
164
+ "tf_legacy_loss": false,
165
+ "tie_encoder_decoder": false,
166
+ "tie_word_embeddings": true,
167
+ "tokenizer_class": null,
168
+ "top_k": 50,
169
+ "top_p": 1.0,
170
+ "torch_dtype": "float32",
171
+ "torchscript": false,
172
+ "transformers_version": "4.25.1",
173
+ "typical_p": 1.0,
174
+ "use_bfloat16": false
175
+ },
176
+ "eos_token_id": 2,
177
+ "is_encoder_decoder": true,
178
+ "length_penalty": 2.0,
179
+ "max_length": 40,
180
+ "model_type": "vision-encoder-decoder",
181
+ "no_repeat_ngram_size": 3,
182
+ "num_beams": 4,
183
+ "pad_token_id": 1,
184
+ "tie_word_embeddings": false,
185
+ "torch_dtype": "float32",
186
+ "transformers_version": null,
187
+ "vocab_size": 250002
188
+ }