tarekziade commited on
Commit
690919f
1 Parent(s): 5e35e06

Upload 15 files

Browse files
config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilvit-flickr",
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "distilbert/distilgpt2",
8
+ "_num_labels": 1,
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": null,
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
+ },
34
+ "initializer_range": 0.02,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0
39
+ },
40
+ "layer_norm_epsilon": 1e-05,
41
+ "length_penalty": 1.0,
42
+ "max_length": 20,
43
+ "min_length": 0,
44
+ "model_type": "gpt2",
45
+ "n_ctx": 1024,
46
+ "n_embd": 768,
47
+ "n_head": 12,
48
+ "n_inner": null,
49
+ "n_layer": 6,
50
+ "n_positions": 1024,
51
+ "no_repeat_ngram_size": 0,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_return_sequences": 1,
55
+ "output_attentions": false,
56
+ "output_hidden_states": false,
57
+ "output_scores": false,
58
+ "pad_token_id": null,
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "reorder_and_upcast_attn": false,
64
+ "repetition_penalty": 1.0,
65
+ "resid_pdrop": 0.1,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "scale_attn_by_inverse_layer_idx": false,
69
+ "scale_attn_weights": true,
70
+ "sep_token_id": null,
71
+ "summary_activation": null,
72
+ "summary_first_dropout": 0.1,
73
+ "summary_proj_to_labels": true,
74
+ "summary_type": "cls_index",
75
+ "summary_use_proj": true,
76
+ "suppress_tokens": null,
77
+ "task_specific_params": {
78
+ "text-generation": {
79
+ "do_sample": true,
80
+ "max_length": 50
81
+ }
82
+ },
83
+ "temperature": 1.0,
84
+ "tf_legacy_loss": false,
85
+ "tie_encoder_decoder": false,
86
+ "tie_word_embeddings": true,
87
+ "tokenizer_class": null,
88
+ "top_k": 50,
89
+ "top_p": 1.0,
90
+ "torch_dtype": null,
91
+ "torchscript": false,
92
+ "typical_p": 1.0,
93
+ "use_bfloat16": false,
94
+ "use_cache": true,
95
+ "vocab_size": 50257
96
+ },
97
+ "decoder_start_token_id": 50256,
98
+ "encoder": {
99
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
100
+ "add_cross_attention": false,
101
+ "architectures": [
102
+ "ViTModel"
103
+ ],
104
+ "attention_probs_dropout_prob": 0.0,
105
+ "bad_words_ids": null,
106
+ "begin_suppress_tokens": null,
107
+ "bos_token_id": null,
108
+ "chunk_size_feed_forward": 0,
109
+ "cross_attention_hidden_size": null,
110
+ "decoder_start_token_id": null,
111
+ "diversity_penalty": 0.0,
112
+ "do_sample": false,
113
+ "early_stopping": false,
114
+ "encoder_no_repeat_ngram_size": 0,
115
+ "encoder_stride": 16,
116
+ "eos_token_id": null,
117
+ "exponential_decay_length_penalty": null,
118
+ "finetuning_task": null,
119
+ "forced_bos_token_id": null,
120
+ "forced_eos_token_id": null,
121
+ "hidden_act": "gelu",
122
+ "hidden_dropout_prob": 0.0,
123
+ "hidden_size": 768,
124
+ "id2label": {
125
+ "0": "LABEL_0",
126
+ "1": "LABEL_1"
127
+ },
128
+ "image_size": 224,
129
+ "initializer_range": 0.02,
130
+ "intermediate_size": 3072,
131
+ "is_decoder": false,
132
+ "is_encoder_decoder": false,
133
+ "label2id": {
134
+ "LABEL_0": 0,
135
+ "LABEL_1": 1
136
+ },
137
+ "layer_norm_eps": 1e-12,
138
+ "length_penalty": 1.0,
139
+ "max_length": 20,
140
+ "min_length": 0,
141
+ "model_type": "vit",
142
+ "no_repeat_ngram_size": 0,
143
+ "num_attention_heads": 12,
144
+ "num_beam_groups": 1,
145
+ "num_beams": 1,
146
+ "num_channels": 3,
147
+ "num_hidden_layers": 12,
148
+ "num_return_sequences": 1,
149
+ "output_attentions": false,
150
+ "output_hidden_states": false,
151
+ "output_scores": false,
152
+ "pad_token_id": null,
153
+ "patch_size": 16,
154
+ "prefix": null,
155
+ "problem_type": null,
156
+ "pruned_heads": {},
157
+ "qkv_bias": true,
158
+ "remove_invalid_values": false,
159
+ "repetition_penalty": 1.0,
160
+ "return_dict": true,
161
+ "return_dict_in_generate": false,
162
+ "sep_token_id": null,
163
+ "suppress_tokens": null,
164
+ "task_specific_params": null,
165
+ "temperature": 1.0,
166
+ "tf_legacy_loss": false,
167
+ "tie_encoder_decoder": false,
168
+ "tie_word_embeddings": true,
169
+ "tokenizer_class": null,
170
+ "top_k": 50,
171
+ "top_p": 1.0,
172
+ "torch_dtype": null,
173
+ "torchscript": false,
174
+ "typical_p": 1.0,
175
+ "use_bfloat16": false
176
+ },
177
+ "eos_token_id": 50256,
178
+ "is_encoder_decoder": true,
179
+ "model_type": "vision-encoder-decoder",
180
+ "pad_token_id": 50256,
181
+ "tie_word_embeddings": false,
182
+ "transformers_version": "4.36.2"
183
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 50256,
3
+ "eos_token_id": 50256,
4
+ "transformers_version": "4.36.2"
5
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76db89dfd123294596415fe30dbfe7dbbd07e3a204e44d4d57f472bd7cdd2184
3
+ size 729979160
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d7b960da19f481ed66e363bc6c526a59be437de84399853a57962bb18e347a
3
+ size 385858911
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f891ec9ff2bc912bae5c05d77d17c6a2e37ff1b897324f9d67825d77cbfd3c
3
+ size 98056673
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:156a30894e0041cf1a89200a9ee73100cfa6fbfc2f4b016fd8d2389be665f75f
3
+ size 343440610
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44c0e7f54e2daee44bbe29c07d047c626b040e9cdda53cf1aa120698f9339cbf
3
+ size 87038150
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTFeatureExtractor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
quantize_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Gemm",
8
+ "Slice",
9
+ "Transpose",
10
+ "Reshape",
11
+ "Where",
12
+ "Sqrt",
13
+ "ReduceMean",
14
+ "Pow",
15
+ "Constant",
16
+ "Tanh",
17
+ "Softmax",
18
+ "Concat",
19
+ "Sub",
20
+ "MatMul",
21
+ "Mul",
22
+ "Range",
23
+ "Gather",
24
+ "Shape",
25
+ "ConstantOfShape",
26
+ "Squeeze",
27
+ "Div",
28
+ "Unsqueeze",
29
+ "Cast",
30
+ "Add",
31
+ "Split"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ },
35
+ "encoder_model": {
36
+ "op_types": [
37
+ "Slice",
38
+ "Transpose",
39
+ "Reshape",
40
+ "Where",
41
+ "Sqrt",
42
+ "ReduceMean",
43
+ "Pow",
44
+ "Constant",
45
+ "Softmax",
46
+ "Concat",
47
+ "Sub",
48
+ "MatMul",
49
+ "Mul",
50
+ "Equal",
51
+ "Gather",
52
+ "Conv",
53
+ "Shape",
54
+ "ConstantOfShape",
55
+ "Div",
56
+ "Unsqueeze",
57
+ "Erf",
58
+ "Add",
59
+ "Expand"
60
+ ],
61
+ "weight_type": "QUInt8"
62
+ }
63
+ }
64
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
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
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2bab3ede229bdd78164c6375de550bcd26938d72edafe93c5acf47a1864de59
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff