dsr commited on
Commit
a8567af
1 Parent(s): 07ab051

Upload poster2plot model

Browse files
Files changed (3) hide show
  1. config.json +173 -0
  2. preprocessor_config.json +17 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": ["VisionEncoderDecoderModel"],
3
+ "decoder": {
4
+ "_name_or_path": "gpt2",
5
+ "activation_function": "gelu_new",
6
+ "add_cross_attention": true,
7
+ "architectures": ["GPT2LMHeadModel"],
8
+ "attn_pdrop": 0.1,
9
+ "bad_words_ids": null,
10
+ "bos_token_id": 50256,
11
+ "chunk_size_feed_forward": 0,
12
+ "cross_attention_hidden_size": null,
13
+ "decoder_start_token_id": null,
14
+ "diversity_penalty": 0.0,
15
+ "do_sample": false,
16
+ "early_stopping": false,
17
+ "embd_pdrop": 0.1,
18
+ "encoder_no_repeat_ngram_size": 0,
19
+ "eos_token_id": 50256,
20
+ "finetuning_task": null,
21
+ "forced_bos_token_id": null,
22
+ "forced_eos_token_id": null,
23
+ "id2label": {
24
+ "0": "LABEL_0",
25
+ "1": "LABEL_1"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "is_decoder": true,
29
+ "is_encoder_decoder": false,
30
+ "label2id": {
31
+ "LABEL_0": 0,
32
+ "LABEL_1": 1
33
+ },
34
+ "layer_norm_epsilon": 1e-5,
35
+ "length_penalty": 1.0,
36
+ "max_length": 20,
37
+ "min_length": 0,
38
+ "model_type": "gpt2",
39
+ "n_ctx": 1024,
40
+ "n_embd": 768,
41
+ "n_head": 12,
42
+ "n_inner": null,
43
+ "n_layer": 12,
44
+ "n_positions": 1024,
45
+ "no_repeat_ngram_size": 0,
46
+ "num_beam_groups": 1,
47
+ "num_beams": 1,
48
+ "num_return_sequences": 1,
49
+ "output_attentions": false,
50
+ "output_hidden_states": false,
51
+ "output_scores": false,
52
+ "pad_token_id": null,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "pruned_heads": {},
56
+ "remove_invalid_values": false,
57
+ "reorder_and_upcast_attn": false,
58
+ "repetition_penalty": 1.0,
59
+ "resid_pdrop": 0.1,
60
+ "return_dict": true,
61
+ "return_dict_in_generate": false,
62
+ "scale_attn_by_inverse_layer_idx": false,
63
+ "scale_attn_weights": true,
64
+ "sep_token_id": null,
65
+ "summary_activation": null,
66
+ "summary_first_dropout": 0.1,
67
+ "summary_proj_to_labels": true,
68
+ "summary_type": "cls_index",
69
+ "summary_use_proj": true,
70
+ "task_specific_params": {
71
+ "text-generation": {
72
+ "do_sample": true,
73
+ "max_length": 50
74
+ }
75
+ },
76
+ "temperature": 1.0,
77
+ "tie_encoder_decoder": false,
78
+ "tie_word_embeddings": true,
79
+ "tokenizer_class": null,
80
+ "top_k": 50,
81
+ "top_p": 1.0,
82
+ "torch_dtype": null,
83
+ "torchscript": false,
84
+ "transformers_version": "4.12.5",
85
+ "use_bfloat16": false,
86
+ "use_cache": true,
87
+ "vocab_size": 50257
88
+ },
89
+ "decoder_start_token_id": 50256,
90
+ "encoder": {
91
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
92
+ "add_cross_attention": false,
93
+ "architectures": ["ViTModel"],
94
+ "attention_probs_dropout_prob": 0.0,
95
+ "bad_words_ids": null,
96
+ "bos_token_id": null,
97
+ "chunk_size_feed_forward": 0,
98
+ "cross_attention_hidden_size": null,
99
+ "decoder_start_token_id": null,
100
+ "diversity_penalty": 0.0,
101
+ "do_sample": false,
102
+ "early_stopping": false,
103
+ "encoder_no_repeat_ngram_size": 0,
104
+ "eos_token_id": null,
105
+ "finetuning_task": null,
106
+ "forced_bos_token_id": null,
107
+ "forced_eos_token_id": null,
108
+ "hidden_act": "gelu",
109
+ "hidden_dropout_prob": 0.0,
110
+ "hidden_size": 768,
111
+ "id2label": {
112
+ "0": "LABEL_0",
113
+ "1": "LABEL_1"
114
+ },
115
+ "image_size": 224,
116
+ "initializer_range": 0.02,
117
+ "intermediate_size": 3072,
118
+ "is_decoder": false,
119
+ "is_encoder_decoder": false,
120
+ "label2id": {
121
+ "LABEL_0": 0,
122
+ "LABEL_1": 1
123
+ },
124
+ "layer_norm_eps": 1e-12,
125
+ "length_penalty": 1.0,
126
+ "max_length": 20,
127
+ "min_length": 0,
128
+ "model_type": "vit",
129
+ "no_repeat_ngram_size": 0,
130
+ "num_attention_heads": 12,
131
+ "num_beam_groups": 1,
132
+ "num_beams": 1,
133
+ "num_channels": 3,
134
+ "num_hidden_layers": 12,
135
+ "num_return_sequences": 1,
136
+ "output_attentions": false,
137
+ "output_hidden_states": false,
138
+ "output_scores": false,
139
+ "pad_token_id": null,
140
+ "patch_size": 16,
141
+ "prefix": null,
142
+ "problem_type": null,
143
+ "pruned_heads": {},
144
+ "qkv_bias": true,
145
+ "remove_invalid_values": false,
146
+ "repetition_penalty": 1.0,
147
+ "return_dict": true,
148
+ "return_dict_in_generate": false,
149
+ "sep_token_id": null,
150
+ "task_specific_params": null,
151
+ "temperature": 1.0,
152
+ "tie_encoder_decoder": false,
153
+ "tie_word_embeddings": true,
154
+ "tokenizer_class": null,
155
+ "top_k": 50,
156
+ "top_p": 1.0,
157
+ "torch_dtype": null,
158
+ "torchscript": false,
159
+ "transformers_version": "4.12.5",
160
+ "use_bfloat16": false
161
+ },
162
+ "is_encoder_decoder": true,
163
+ "length_penalty": 2.0,
164
+ "max_length": 64,
165
+ "model_type": "vision-encoder-decoder",
166
+ "no_repeat_ngram_size": 3,
167
+ "num_beams": 4,
168
+ "pad_token_id": 50256,
169
+ "tie_word_embeddings": false,
170
+ "torch_dtype": "float32",
171
+ "transformers_version": null,
172
+ "vocab_size": 50257
173
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "ViTFeatureExtractor",
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_std": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "resample": 2,
16
+ "size": 224
17
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a736baeaf505c1d2722a27c7e28c6c10b89fabcad48e7a14a8bd253d355ce94
3
+ size 982141993