Xenova HF staff commited on
Commit
54b5f17
1 Parent(s): b7ae766

Upload 16 files

Browse files
config.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "dc68f91c06a1ba6f15268e5b9c13ae7a7c514084",
3
+ "_name_or_path": "nlpconnect/vit-gpt2-image-captioning",
4
+ "architectures": [
5
+ "VisionEncoderDecoderModel"
6
+ ],
7
+ "bos_token_id": 50256,
8
+ "decoder": {
9
+ "_name_or_path": "",
10
+ "activation_function": "gelu_new",
11
+ "add_cross_attention": true,
12
+ "architectures": [
13
+ "GPT2LMHeadModel"
14
+ ],
15
+ "attn_pdrop": 0.1,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 50256,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": 50256,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "early_stopping": false,
25
+ "embd_pdrop": 0.1,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 50256,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "is_decoder": true,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1
42
+ },
43
+ "layer_norm_epsilon": 1e-05,
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "min_length": 0,
47
+ "model_type": "gpt2",
48
+ "n_ctx": 1024,
49
+ "n_embd": 768,
50
+ "n_head": 12,
51
+ "n_inner": null,
52
+ "n_layer": 12,
53
+ "n_positions": 1024,
54
+ "no_repeat_ngram_size": 0,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_return_sequences": 1,
58
+ "output_attentions": false,
59
+ "output_hidden_states": false,
60
+ "output_scores": false,
61
+ "pad_token_id": 50256,
62
+ "prefix": null,
63
+ "problem_type": null,
64
+ "pruned_heads": {},
65
+ "remove_invalid_values": false,
66
+ "reorder_and_upcast_attn": false,
67
+ "repetition_penalty": 1.0,
68
+ "resid_pdrop": 0.1,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "scale_attn_by_inverse_layer_idx": false,
72
+ "scale_attn_weights": true,
73
+ "sep_token_id": null,
74
+ "summary_activation": null,
75
+ "summary_first_dropout": 0.1,
76
+ "summary_proj_to_labels": true,
77
+ "summary_type": "cls_index",
78
+ "summary_use_proj": true,
79
+ "suppress_tokens": null,
80
+ "task_specific_params": {
81
+ "text-generation": {
82
+ "do_sample": true,
83
+ "max_length": 50
84
+ }
85
+ },
86
+ "temperature": 1.0,
87
+ "tf_legacy_loss": false,
88
+ "tie_encoder_decoder": false,
89
+ "tie_word_embeddings": true,
90
+ "tokenizer_class": null,
91
+ "top_k": 50,
92
+ "top_p": 1.0,
93
+ "torch_dtype": null,
94
+ "torchscript": false,
95
+ "transformers_version": "4.28.1",
96
+ "typical_p": 1.0,
97
+ "use_bfloat16": false,
98
+ "use_cache": true,
99
+ "vocab_size": 50257
100
+ },
101
+ "decoder_start_token_id": 50256,
102
+ "encoder": {
103
+ "_name_or_path": "",
104
+ "add_cross_attention": false,
105
+ "architectures": [
106
+ "ViTModel"
107
+ ],
108
+ "attention_probs_dropout_prob": 0.0,
109
+ "bad_words_ids": null,
110
+ "begin_suppress_tokens": null,
111
+ "bos_token_id": null,
112
+ "chunk_size_feed_forward": 0,
113
+ "cross_attention_hidden_size": null,
114
+ "decoder_start_token_id": null,
115
+ "diversity_penalty": 0.0,
116
+ "do_sample": false,
117
+ "early_stopping": false,
118
+ "encoder_no_repeat_ngram_size": 0,
119
+ "encoder_stride": 16,
120
+ "eos_token_id": null,
121
+ "exponential_decay_length_penalty": null,
122
+ "finetuning_task": null,
123
+ "forced_bos_token_id": null,
124
+ "forced_eos_token_id": null,
125
+ "hidden_act": "gelu",
126
+ "hidden_dropout_prob": 0.0,
127
+ "hidden_size": 768,
128
+ "id2label": {
129
+ "0": "LABEL_0",
130
+ "1": "LABEL_1"
131
+ },
132
+ "image_size": 224,
133
+ "initializer_range": 0.02,
134
+ "intermediate_size": 3072,
135
+ "is_decoder": false,
136
+ "is_encoder_decoder": false,
137
+ "label2id": {
138
+ "LABEL_0": 0,
139
+ "LABEL_1": 1
140
+ },
141
+ "layer_norm_eps": 1e-12,
142
+ "length_penalty": 1.0,
143
+ "max_length": 20,
144
+ "min_length": 0,
145
+ "model_type": "vit",
146
+ "no_repeat_ngram_size": 0,
147
+ "num_attention_heads": 12,
148
+ "num_beam_groups": 1,
149
+ "num_beams": 1,
150
+ "num_channels": 3,
151
+ "num_hidden_layers": 12,
152
+ "num_return_sequences": 1,
153
+ "output_attentions": false,
154
+ "output_hidden_states": false,
155
+ "output_scores": false,
156
+ "pad_token_id": null,
157
+ "patch_size": 16,
158
+ "prefix": null,
159
+ "problem_type": null,
160
+ "pruned_heads": {},
161
+ "qkv_bias": true,
162
+ "remove_invalid_values": false,
163
+ "repetition_penalty": 1.0,
164
+ "return_dict": true,
165
+ "return_dict_in_generate": false,
166
+ "sep_token_id": null,
167
+ "suppress_tokens": null,
168
+ "task_specific_params": null,
169
+ "temperature": 1.0,
170
+ "tf_legacy_loss": false,
171
+ "tie_encoder_decoder": false,
172
+ "tie_word_embeddings": true,
173
+ "tokenizer_class": null,
174
+ "top_k": 50,
175
+ "top_p": 1.0,
176
+ "torch_dtype": null,
177
+ "torchscript": false,
178
+ "transformers_version": "4.28.1",
179
+ "typical_p": 1.0,
180
+ "use_bfloat16": false
181
+ },
182
+ "eos_token_id": 50256,
183
+ "is_encoder_decoder": true,
184
+ "model_type": "vision-encoder-decoder",
185
+ "pad_token_id": 50256,
186
+ "tie_word_embeddings": false,
187
+ "torch_dtype": "float32",
188
+ "transformers_version": null
189
+ }
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": "4.28.1"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ccda5621cb75ac4cf79164578638571d769b04c94c348f83c5b2490ab7f13a6
3
+ size 767520869
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d80260f67e8b1234b811d7e529ab29b11c0c3c0da2b903dde0a438889a424378
3
+ size 768369266
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0fb7df936cd404f61426861e7fb91e3143bcf1338068f7e2ca5c97a062b2321
3
+ size 195555265
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d55c5029517e78e50c18b1eef1ddc33669409836c9ec7e3fb8cb780bd48add1d
3
+ size 194279031
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0556fa33bae38f98f2a8595c02e7489aec5c99c4bf59ff37778360745147526
3
+ size 767518177
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe0f96f29384416db432aa71cc7302d9bfb253a79de8a274ae4d3029a29c9f4c
3
+ size 194270894
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14e343f8fe7c0ca8f057bc9735ec2031278ab787b5fc42430173e4539a893020
3
+ size 343440631
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6671babe3eeeea2056a203044c3ed895eafd3e4687af374d84c537ab3e707e
3
+ size 87038140
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 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff