ycchen commited on
Commit
f14a55e
1 Parent(s): 5a3db14
Files changed (2) hide show
  1. config.json +207 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "beit_macbert_base_v3_aicup_ft/best",
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "./macbert-base-last6",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "BertForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": null,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "directionality": "bidi",
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": null,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "gradient_checkpointing": false,
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-12,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 512,
49
+ "min_length": 0,
50
+ "model_type": "bert",
51
+ "no_repeat_ngram_size": 0,
52
+ "num_attention_heads": 12,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_hidden_layers": 6,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 0,
61
+ "pooler_fc_size": 768,
62
+ "pooler_num_attention_heads": 12,
63
+ "pooler_num_fc_layers": 3,
64
+ "pooler_size_per_head": 128,
65
+ "pooler_type": "first_token_transform",
66
+ "position_embedding_type": "absolute",
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
+ "sep_token_id": 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": "float32",
84
+ "torchscript": false,
85
+ "transformers_version": "4.21.1",
86
+ "type_vocab_size": 2,
87
+ "typical_p": 1.0,
88
+ "use_bfloat16": false,
89
+ "use_cache": true,
90
+ "vocab_size": 21128
91
+ },
92
+ "decoder_start_token_id": 101,
93
+ "early_stopping": true,
94
+ "encoder": {
95
+ "_name_or_path": "microsoft/beit-base-patch16-224-pt22k",
96
+ "add_cross_attention": false,
97
+ "architectures": [
98
+ "BeitForMaskedImageModeling"
99
+ ],
100
+ "attention_probs_dropout_prob": 0.0,
101
+ "auxiliary_channels": 256,
102
+ "auxiliary_concat_input": false,
103
+ "auxiliary_loss_weight": 0.4,
104
+ "auxiliary_num_convs": 1,
105
+ "bad_words_ids": null,
106
+ "bos_token_id": null,
107
+ "chunk_size_feed_forward": 0,
108
+ "cross_attention_hidden_size": null,
109
+ "decoder_start_token_id": null,
110
+ "diversity_penalty": 0.0,
111
+ "do_sample": false,
112
+ "drop_path_rate": 0.1,
113
+ "early_stopping": false,
114
+ "encoder_no_repeat_ngram_size": 0,
115
+ "eos_token_id": null,
116
+ "exponential_decay_length_penalty": null,
117
+ "finetuning_task": null,
118
+ "forced_bos_token_id": null,
119
+ "forced_eos_token_id": null,
120
+ "hidden_act": "gelu",
121
+ "hidden_dropout_prob": 0.0,
122
+ "hidden_size": 768,
123
+ "id2label": {
124
+ "0": "LABEL_0",
125
+ "1": "LABEL_1"
126
+ },
127
+ "image_size": 224,
128
+ "initializer_range": 0.02,
129
+ "intermediate_size": 3072,
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-12,
137
+ "layer_scale_init_value": 0.1,
138
+ "length_penalty": 1.0,
139
+ "max_length": 20,
140
+ "min_length": 0,
141
+ "model_type": "beit",
142
+ "no_repeat_ngram_size": 0,
143
+ "num_attention_heads": 12,
144
+ "num_beam_groups": 1,
145
+ "num_beams": 1,
146
+ "num_channels": 3,
147
+ "num_hidden_layers": 12,
148
+ "num_return_sequences": 1,
149
+ "out_indices": [
150
+ 3,
151
+ 5,
152
+ 7,
153
+ 11
154
+ ],
155
+ "output_attentions": false,
156
+ "output_hidden_states": false,
157
+ "output_scores": false,
158
+ "pad_token_id": null,
159
+ "patch_size": 16,
160
+ "pool_scales": [
161
+ 1,
162
+ 2,
163
+ 3,
164
+ 6
165
+ ],
166
+ "prefix": null,
167
+ "problem_type": null,
168
+ "pruned_heads": {},
169
+ "remove_invalid_values": false,
170
+ "repetition_penalty": 1.0,
171
+ "return_dict": true,
172
+ "return_dict_in_generate": false,
173
+ "semantic_loss_ignore_index": 255,
174
+ "sep_token_id": null,
175
+ "task_specific_params": null,
176
+ "temperature": 1.0,
177
+ "tf_legacy_loss": false,
178
+ "tie_encoder_decoder": false,
179
+ "tie_word_embeddings": true,
180
+ "tokenizer_class": null,
181
+ "top_k": 50,
182
+ "top_p": 1.0,
183
+ "torch_dtype": "float32",
184
+ "torchscript": false,
185
+ "transformers_version": "4.21.1",
186
+ "typical_p": 1.0,
187
+ "use_absolute_position_embeddings": false,
188
+ "use_auxiliary_head": true,
189
+ "use_bfloat16": false,
190
+ "use_mask_token": true,
191
+ "use_mean_pooling": true,
192
+ "use_relative_position_bias": false,
193
+ "use_shared_relative_position_bias": true,
194
+ "vocab_size": 8192
195
+ },
196
+ "eos_token_id": 102,
197
+ "is_encoder_decoder": true,
198
+ "length_penalty": 2.0,
199
+ "max_length": 12,
200
+ "model_type": "vision-encoder-decoder",
201
+ "no_repeat_ngram_size": 3,
202
+ "pad_token_id": 0,
203
+ "tie_word_embeddings": false,
204
+ "torch_dtype": "float32",
205
+ "transformers_version": null,
206
+ "vocab_size": 21128
207
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a383073adc74b1f4100a10c5f7d4d1f1e9554ffbeb4834cf130cffb5cdd67a38
3
+ size 638893963