sachin commited on
Commit
551993e
1 Parent(s): fd662dd
Files changed (2) hide show
  1. config.json +171 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VisionEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "distilgpt2",
7
+ "_num_labels": 1,
8
+ "activation_function": "gelu_new",
9
+ "add_cross_attention": true,
10
+ "architectures": [
11
+ "GPT2LMHeadModel"
12
+ ],
13
+ "attn_pdrop": 0.1,
14
+ "bad_words_ids": null,
15
+ "bos_token_id": 50256,
16
+ "chunk_size_feed_forward": 0,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "embd_pdrop": 0.1,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 50256,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "id2label": {
29
+ "0": "LABEL_0"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "is_decoder": true,
33
+ "is_encoder_decoder": false,
34
+ "label2id": {
35
+ "LABEL_0": 0
36
+ },
37
+ "layer_norm_epsilon": 1e-05,
38
+ "length_penalty": 1.0,
39
+ "max_length": 20,
40
+ "min_length": 0,
41
+ "model_type": "gpt2",
42
+ "n_ctx": 1024,
43
+ "n_embd": 768,
44
+ "n_head": 12,
45
+ "n_inner": null,
46
+ "n_layer": 6,
47
+ "n_positions": 1024,
48
+ "no_repeat_ngram_size": 0,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_return_sequences": 1,
52
+ "output_attentions": false,
53
+ "output_hidden_states": false,
54
+ "output_scores": false,
55
+ "pad_token_id": null,
56
+ "prefix": null,
57
+ "problem_type": null,
58
+ "pruned_heads": {},
59
+ "remove_invalid_values": false,
60
+ "reorder_and_upcast_attn": false,
61
+ "repetition_penalty": 1.0,
62
+ "resid_pdrop": 0.1,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "scale_attn_by_inverse_layer_idx": false,
66
+ "scale_attn_weights": true,
67
+ "sep_token_id": null,
68
+ "summary_activation": null,
69
+ "summary_first_dropout": 0.1,
70
+ "summary_proj_to_labels": true,
71
+ "summary_type": "cls_index",
72
+ "summary_use_proj": true,
73
+ "task_specific_params": {
74
+ "text-generation": {
75
+ "do_sample": true,
76
+ "max_length": 50
77
+ }
78
+ },
79
+ "temperature": 1.0,
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": "4.12.5",
88
+ "use_bfloat16": false,
89
+ "use_cache": true,
90
+ "vocab_size": 50257
91
+ },
92
+ "encoder": {
93
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
94
+ "add_cross_attention": false,
95
+ "architectures": [
96
+ "ViTModel"
97
+ ],
98
+ "attention_probs_dropout_prob": 0.0,
99
+ "bad_words_ids": null,
100
+ "bos_token_id": null,
101
+ "chunk_size_feed_forward": 0,
102
+ "cross_attention_hidden_size": null,
103
+ "decoder_start_token_id": null,
104
+ "diversity_penalty": 0.0,
105
+ "do_sample": false,
106
+ "early_stopping": false,
107
+ "encoder_no_repeat_ngram_size": 0,
108
+ "eos_token_id": null,
109
+ "finetuning_task": null,
110
+ "forced_bos_token_id": null,
111
+ "forced_eos_token_id": null,
112
+ "hidden_act": "gelu",
113
+ "hidden_dropout_prob": 0.0,
114
+ "hidden_size": 768,
115
+ "id2label": {
116
+ "0": "LABEL_0",
117
+ "1": "LABEL_1"
118
+ },
119
+ "image_size": 224,
120
+ "initializer_range": 0.02,
121
+ "intermediate_size": 3072,
122
+ "is_decoder": false,
123
+ "is_encoder_decoder": false,
124
+ "label2id": {
125
+ "LABEL_0": 0,
126
+ "LABEL_1": 1
127
+ },
128
+ "layer_norm_eps": 1e-12,
129
+ "length_penalty": 1.0,
130
+ "max_length": 20,
131
+ "min_length": 0,
132
+ "model_type": "vit",
133
+ "no_repeat_ngram_size": 0,
134
+ "num_attention_heads": 12,
135
+ "num_beam_groups": 1,
136
+ "num_beams": 1,
137
+ "num_channels": 3,
138
+ "num_hidden_layers": 12,
139
+ "num_return_sequences": 1,
140
+ "output_attentions": false,
141
+ "output_hidden_states": false,
142
+ "output_scores": false,
143
+ "pad_token_id": null,
144
+ "patch_size": 16,
145
+ "prefix": null,
146
+ "problem_type": null,
147
+ "pruned_heads": {},
148
+ "qkv_bias": true,
149
+ "remove_invalid_values": false,
150
+ "repetition_penalty": 1.0,
151
+ "return_dict": true,
152
+ "return_dict_in_generate": false,
153
+ "sep_token_id": null,
154
+ "task_specific_params": null,
155
+ "temperature": 1.0,
156
+ "tie_encoder_decoder": false,
157
+ "tie_word_embeddings": true,
158
+ "tokenizer_class": null,
159
+ "top_k": 50,
160
+ "top_p": 1.0,
161
+ "torch_dtype": null,
162
+ "torchscript": false,
163
+ "transformers_version": "4.12.5",
164
+ "use_bfloat16": false
165
+ },
166
+ "is_encoder_decoder": true,
167
+ "model_type": "vision-encoder-decoder",
168
+ "tie_word_embeddings": false,
169
+ "torch_dtype": "float32",
170
+ "transformers_version": null
171
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9068962201c403f7d4a976f02e99a876a4d409d3ff55fe2619ca44f17b158b13
3
+ size 742656521