Hugging Face's logo

dumperize
/
movie-picture-captioning

Image-to-Text
Transformers
PyTorch
Russian
vision-encoder-decoder
Inference Endpoints
Model card Files Community
1
dumperize commited on
Commit
3c76762
•
1 Parent(s): f253902

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +182 -182
config.json CHANGED
@@ -1,189 +1,189 @@
1
  {
2
- "_commit_hash": null,
3
- "_name_or_path": "/content/drive/MyDrive/checkpoint-310000/",
4
- "architectures": [
5
- "VisionEncoderDecoderModel"
6
- ],
7
- "decoder": {
8
- "_name_or_path": "DeepPavlov/rubert-base-cased",
9
- "add_cross_attention": true,
10
  "architectures": [
11
- "BertModel"
12
  ],
13
- "attention_probs_dropout_prob": 0.1,
14
- "bad_words_ids": null,
15
- "begin_suppress_tokens": null,
16
- "bos_token_id": null,
17
- "chunk_size_feed_forward": 0,
18
- "classifier_dropout": null,
19
- "cross_attention_hidden_size": null,
20
- "decoder_start_token_id": null,
21
- "directionality": "bidi",
22
- "diversity_penalty": 0.0,
23
- "do_sample": false,
24
- "early_stopping": false,
25
- "encoder_no_repeat_ngram_size": 0,
26
- "eos_token_id": null,
27
- "exponential_decay_length_penalty": null,
28
- "finetuning_task": null,
29
- "forced_bos_token_id": null,
30
- "forced_eos_token_id": null,
31
- "hidden_act": "gelu",
32
- "hidden_dropout_prob": 0.1,
33
- "hidden_size": 768,
34
- "id2label": {
35
- "0": "LABEL_0",
36
- "1": "LABEL_1"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  },
38
- "initializer_range": 0.02,
39
- "intermediate_size": 3072,
40
- "is_decoder": true,
41
- "is_encoder_decoder": false,
42
- "label2id": {
43
- "LABEL_0": 0,
44
- "LABEL_1": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  },
46
- "layer_norm_eps": 1e-12,
47
- "length_penalty": 1.0,
48
- "max_length": 20,
49
- "max_position_embeddings": 512,
50
- "min_length": 0,
51
- "model_type": "bert",
52
- "no_repeat_ngram_size": 0,
53
- "num_attention_heads": 12,
54
- "num_beam_groups": 1,
55
- "num_beams": 1,
56
- "num_hidden_layers": 12,
57
- "num_return_sequences": 1,
58
- "output_attentions": false,
59
- "output_hidden_states": false,
60
- "output_past": true,
61
- "output_scores": false,
62
  "pad_token_id": 0,
63
- "pooler_fc_size": 768,
64
- "pooler_num_attention_heads": 12,
65
- "pooler_num_fc_layers": 3,
66
- "pooler_size_per_head": 128,
67
- "pooler_type": "first_token_transform",
68
- "position_embedding_type": "absolute",
69
- "prefix": null,
70
- "problem_type": null,
71
- "pruned_heads": {},
72
- "remove_invalid_values": false,
73
- "repetition_penalty": 1.0,
74
- "return_dict": true,
75
- "return_dict_in_generate": false,
76
- "sep_token_id": null,
77
- "suppress_tokens": null,
78
- "task_specific_params": null,
79
- "temperature": 1.0,
80
- "tf_legacy_loss": false,
81
- "tie_encoder_decoder": false,
82
- "tie_word_embeddings": true,
83
- "tokenizer_class": null,
84
- "top_k": 50,
85
- "top_p": 1.0,
86
- "torch_dtype": null,
87
- "torchscript": false,
88
- "transformers_version": "4.25.1",
89
- "type_vocab_size": 2,
90
- "typical_p": 1.0,
91
- "use_bfloat16": false,
92
- "use_cache": true,
93
  "vocab_size": 119547
94
- },
95
- "decoder_start_token_id": 101,
96
- "early_stopping": true,
97
- "encoder": {
98
- "_name_or_path": "google/vit-base-patch16-224-in21k",
99
- "add_cross_attention": false,
100
- "architectures": [
101
- "ViTModel"
102
- ],
103
- "attention_probs_dropout_prob": 0.0,
104
- "bad_words_ids": null,
105
- "begin_suppress_tokens": 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
- "early_stopping": false,
113
- "encoder_no_repeat_ngram_size": 0,
114
- "encoder_stride": 16,
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
- "length_penalty": 1.0,
138
- "max_length": 20,
139
- "min_length": 0,
140
- "model_type": "vit",
141
- "no_repeat_ngram_size": 0,
142
- "num_attention_heads": 12,
143
- "num_beam_groups": 1,
144
- "num_beams": 1,
145
- "num_channels": 3,
146
- "num_hidden_layers": 12,
147
- "num_return_sequences": 1,
148
- "output_attentions": false,
149
- "output_hidden_states": false,
150
- "output_scores": false,
151
- "pad_token_id": null,
152
- "patch_size": 16,
153
- "prefix": null,
154
- "problem_type": null,
155
- "pruned_heads": {},
156
- "qkv_bias": true,
157
- "remove_invalid_values": false,
158
- "repetition_penalty": 1.0,
159
- "return_dict": true,
160
- "return_dict_in_generate": false,
161
- "sep_token_id": null,
162
- "suppress_tokens": null,
163
- "task_specific_params": null,
164
- "temperature": 1.0,
165
- "tf_legacy_loss": false,
166
- "tie_encoder_decoder": false,
167
- "tie_word_embeddings": true,
168
- "tokenizer_class": null,
169
- "top_k": 50,
170
- "top_p": 1.0,
171
- "torch_dtype": null,
172
- "torchscript": false,
173
- "transformers_version": "4.25.1",
174
- "typical_p": 1.0,
175
- "use_bfloat16": false
176
- },
177
- "eos_token_id": 102,
178
- "is_encoder_decoder": true,
179
- "length_penalty": 2.0,
180
- "max_length": 64,
181
- "model_type": "vision-encoder-decoder",
182
- "no_repeat_ngram_size": 3,
183
- "num_beams": 4,
184
- "pad_token_id": 0,
185
- "tie_word_embeddings": false,
186
- "torch_dtype": "float32",
187
- "transformers_version": null,
188
- "vocab_size": 119547
189
- }
 
1
  {
2
+ "_commit_hash": null,
 
 
 
 
 
 
 
3
  "architectures": [
4
+ "VisionEncoderDecoderModel"
5
  ],
6
+ "decoder": {
7
+ "_name_or_path": "DeepPavlov/rubert-base-cased",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "BertModel"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": null,
16
+ "chunk_size_feed_forward": 0,
17
+ "classifier_dropout": null,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "directionality": "bidi",
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": null,
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-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": 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": 0,
62
+ "pooler_fc_size": 768,
63
+ "pooler_num_attention_heads": 12,
64
+ "pooler_num_fc_layers": 3,
65
+ "pooler_size_per_head": 128,
66
+ "pooler_type": "first_token_transform",
67
+ "position_embedding_type": "absolute",
68
+ "prefix": null,
69
+ "problem_type": null,
70
+ "pruned_heads": {},
71
+ "remove_invalid_values": false,
72
+ "repetition_penalty": 1.0,
73
+ "return_dict": true,
74
+ "return_dict_in_generate": false,
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": true,
82
+ "tokenizer_class": null,
83
+ "top_k": 50,
84
+ "top_p": 1.0,
85
+ "torch_dtype": null,
86
+ "torchscript": false,
87
+ "transformers_version": "4.24.0",
88
+ "type_vocab_size": 2,
89
+ "typical_p": 1.0,
90
+ "use_bfloat16": false,
91
+ "use_cache": true,
92
+ "vocab_size": 119547
93
  },
94
+ "decoder_start_token_id": 101,
95
+ "early_stopping": true,
96
+ "encoder": {
97
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
98
+ "add_cross_attention": false,
99
+ "architectures": [
100
+ "ViTModel"
101
+ ],
102
+ "attention_probs_dropout_prob": 0.0,
103
+ "bad_words_ids": null,
104
+ "begin_suppress_tokens": null,
105
+ "bos_token_id": null,
106
+ "chunk_size_feed_forward": 0,
107
+ "cross_attention_hidden_size": null,
108
+ "decoder_start_token_id": null,
109
+ "diversity_penalty": 0.0,
110
+ "do_sample": false,
111
+ "early_stopping": false,
112
+ "encoder_no_repeat_ngram_size": 0,
113
+ "encoder_stride": 16,
114
+ "eos_token_id": null,
115
+ "exponential_decay_length_penalty": null,
116
+ "finetuning_task": null,
117
+ "forced_bos_token_id": null,
118
+ "forced_eos_token_id": null,
119
+ "hidden_act": "gelu",
120
+ "hidden_dropout_prob": 0.0,
121
+ "hidden_size": 768,
122
+ "id2label": {
123
+ "0": "LABEL_0",
124
+ "1": "LABEL_1"
125
+ },
126
+ "image_size": 224,
127
+ "initializer_range": 0.02,
128
+ "intermediate_size": 3072,
129
+ "is_decoder": false,
130
+ "is_encoder_decoder": false,
131
+ "label2id": {
132
+ "LABEL_0": 0,
133
+ "LABEL_1": 1
134
+ },
135
+ "layer_norm_eps": 1e-12,
136
+ "length_penalty": 1.0,
137
+ "max_length": 20,
138
+ "min_length": 0,
139
+ "model_type": "vit",
140
+ "no_repeat_ngram_size": 0,
141
+ "num_attention_heads": 12,
142
+ "num_beam_groups": 1,
143
+ "num_beams": 1,
144
+ "num_channels": 3,
145
+ "num_hidden_layers": 12,
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": "BertTokenizer",
168
+ "top_k": 50,
169
+ "top_p": 1.0,
170
+ "torch_dtype": null,
171
+ "torchscript": false,
172
+ "transformers_version": "4.24.0",
173
+ "typical_p": 1.0,
174
+ "use_bfloat16": false
175
  },
176
+ "eos_token_id": 102,
177
+ "is_encoder_decoder": true,
178
+ "length_penalty": 2.0,
179
+ "max_length": 64,
180
+ "model_type": "vision-encoder-decoder",
181
+ "no_repeat_ngram_size": 3,
182
+ "num_beams": 4,
 
 
 
 
 
 
 
 
 
183
  "pad_token_id": 0,
184
+ "tie_word_embeddings": false,
185
+ "torch_dtype": "float32",
186
+ "transformers_version": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
187
  "vocab_size": 119547
188
+ }
189
+