Centaur31 commited on
Commit
82a0e2c
1 Parent(s): 2ba14b4

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nlpconnect/vit-gpt2-image-captioning",
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "bos_token_id": 50256,
7
+ "decoder": {
8
+ "_name_or_path": "",
9
+ "activation_function": "gelu_new",
10
+ "add_cross_attention": true,
11
+ "architectures": [
12
+ "GPT2LMHeadModel"
13
+ ],
14
+ "attn_pdrop": 0.1,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": 50256,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": 50256,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "early_stopping": false,
24
+ "embd_pdrop": 0.1,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": 50256,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_epsilon": 1e-05,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "min_length": 0,
46
+ "model_type": "gpt2",
47
+ "n_ctx": 1024,
48
+ "n_embd": 768,
49
+ "n_head": 12,
50
+ "n_inner": null,
51
+ "n_layer": 12,
52
+ "n_positions": 1024,
53
+ "no_repeat_ngram_size": 0,
54
+ "num_beam_groups": 1,
55
+ "num_beams": 1,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 50256,
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "reorder_and_upcast_attn": false,
66
+ "repetition_penalty": 1.0,
67
+ "resid_pdrop": 0.1,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "scale_attn_by_inverse_layer_idx": false,
71
+ "scale_attn_weights": true,
72
+ "sep_token_id": null,
73
+ "summary_activation": null,
74
+ "summary_first_dropout": 0.1,
75
+ "summary_proj_to_labels": true,
76
+ "summary_type": "cls_index",
77
+ "summary_use_proj": true,
78
+ "suppress_tokens": null,
79
+ "task_specific_params": {
80
+ "text-generation": {
81
+ "do_sample": true,
82
+ "max_length": 50
83
+ }
84
+ },
85
+ "temperature": 1.0,
86
+ "tf_legacy_loss": false,
87
+ "tie_encoder_decoder": false,
88
+ "tie_word_embeddings": true,
89
+ "tokenizer_class": null,
90
+ "top_k": 50,
91
+ "top_p": 1.0,
92
+ "torch_dtype": null,
93
+ "torchscript": false,
94
+ "typical_p": 1.0,
95
+ "use_bfloat16": false,
96
+ "use_cache": true,
97
+ "vocab_size": 50257
98
+ },
99
+ "decoder_start_token_id": 50256,
100
+ "encoder": {
101
+ "_name_or_path": "",
102
+ "add_cross_attention": false,
103
+ "architectures": [
104
+ "ViTModel"
105
+ ],
106
+ "attention_probs_dropout_prob": 0.0,
107
+ "bad_words_ids": null,
108
+ "begin_suppress_tokens": null,
109
+ "bos_token_id": null,
110
+ "chunk_size_feed_forward": 0,
111
+ "cross_attention_hidden_size": null,
112
+ "decoder_start_token_id": null,
113
+ "diversity_penalty": 0.0,
114
+ "do_sample": false,
115
+ "early_stopping": false,
116
+ "encoder_no_repeat_ngram_size": 0,
117
+ "encoder_stride": 16,
118
+ "eos_token_id": null,
119
+ "exponential_decay_length_penalty": null,
120
+ "finetuning_task": null,
121
+ "forced_bos_token_id": null,
122
+ "forced_eos_token_id": null,
123
+ "hidden_act": "gelu",
124
+ "hidden_dropout_prob": 0.0,
125
+ "hidden_size": 768,
126
+ "id2label": {
127
+ "0": "LABEL_0",
128
+ "1": "LABEL_1"
129
+ },
130
+ "image_size": 224,
131
+ "initializer_range": 0.02,
132
+ "intermediate_size": 3072,
133
+ "is_decoder": false,
134
+ "is_encoder_decoder": false,
135
+ "label2id": {
136
+ "LABEL_0": 0,
137
+ "LABEL_1": 1
138
+ },
139
+ "layer_norm_eps": 1e-12,
140
+ "length_penalty": 1.0,
141
+ "max_length": 20,
142
+ "min_length": 0,
143
+ "model_type": "vit",
144
+ "no_repeat_ngram_size": 0,
145
+ "num_attention_heads": 12,
146
+ "num_beam_groups": 1,
147
+ "num_beams": 1,
148
+ "num_channels": 3,
149
+ "num_hidden_layers": 12,
150
+ "num_return_sequences": 1,
151
+ "output_attentions": false,
152
+ "output_hidden_states": false,
153
+ "output_scores": false,
154
+ "pad_token_id": null,
155
+ "patch_size": 16,
156
+ "prefix": null,
157
+ "problem_type": null,
158
+ "pruned_heads": {},
159
+ "qkv_bias": true,
160
+ "remove_invalid_values": false,
161
+ "repetition_penalty": 1.0,
162
+ "return_dict": true,
163
+ "return_dict_in_generate": false,
164
+ "sep_token_id": null,
165
+ "suppress_tokens": null,
166
+ "task_specific_params": null,
167
+ "temperature": 1.0,
168
+ "tf_legacy_loss": false,
169
+ "tie_encoder_decoder": false,
170
+ "tie_word_embeddings": true,
171
+ "tokenizer_class": null,
172
+ "top_k": 50,
173
+ "top_p": 1.0,
174
+ "torch_dtype": null,
175
+ "torchscript": false,
176
+ "typical_p": 1.0,
177
+ "use_bfloat16": false
178
+ },
179
+ "eos_token_id": 50256,
180
+ "is_encoder_decoder": true,
181
+ "model_type": "vision-encoder-decoder",
182
+ "pad_token_id": 50256,
183
+ "tie_word_embeddings": false,
184
+ "torch_dtype": "float32",
185
+ "transformers_version": "4.35.2"
186
+ }
decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34e54e613064e4955570f729c040be0376b20150b10c47a98b803d2cb9a95bee
3
+ size 767518619
decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f915774c235412ac3d17fe255676c45102a40b0335e81eab6e27ccce6950697
3
+ size 767515927
encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89850ce9e4229924921166a3b8d518d46a3f510d87ca6814b5bb1cb8c5457d22
3
+ size 343440610
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "decoder_start_token_id": 50256,
5
+ "eos_token_id": 50256,
6
+ "pad_token_id": 50256,
7
+ "transformers_version": "4.35.2"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "feature_extractor_type": "ViTFeatureExtractor",
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "ViTFeatureExtractor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "resample": 2,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "max_length": 32,
17
+ "model_max_length": 1024,
18
+ "pad_to_multiple_of": null,
19
+ "pad_token": "<|endoftext|>",
20
+ "pad_token_type_id": 0,
21
+ "padding_side": "right",
22
+ "stride": 0,
23
+ "tokenizer_class": "GPT2Tokenizer",
24
+ "truncation_side": "right",
25
+ "truncation_strategy": "longest_first",
26
+ "unk_token": "<|endoftext|>"
27
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff