CondadosAI commited on
Commit
eb404b5
·
verified ·
1 Parent(s): 6b22039

weights: mirror microsoft/xclip-base-patch32 @ a2e27a78 (safetensors-only; pickle omitted for security)

Browse files
config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "XClipModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "xclip",
9
+ "projection_dim": 512,
10
+ "prompt_alpha": 0.1,
11
+ "prompt_attention_dropout": 0.0,
12
+ "prompt_hidden_act": "quick_gelu",
13
+ "prompt_layers": 2,
14
+ "prompt_num_attention_heads": 8,
15
+ "prompt_projection_dropout": 0.0,
16
+ "text_config": {
17
+ "_name_or_path": "",
18
+ "add_cross_attention": false,
19
+ "architectures": null,
20
+ "attention_dropout": 0.0,
21
+ "bad_words_ids": null,
22
+ "bos_token_id": 0,
23
+ "chunk_size_feed_forward": 0,
24
+ "cross_attention_hidden_size": null,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "dropout": 0.0,
29
+ "early_stopping": false,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": 2,
32
+ "exponential_decay_length_penalty": null,
33
+ "finetuning_task": null,
34
+ "forced_bos_token_id": null,
35
+ "forced_eos_token_id": null,
36
+ "hidden_act": "quick_gelu",
37
+ "hidden_size": 512,
38
+ "id2label": {
39
+ "0": "LABEL_0",
40
+ "1": "LABEL_1"
41
+ },
42
+ "initializer_factor": 1.0,
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 2048,
45
+ "is_decoder": false,
46
+ "is_encoder_decoder": false,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
+ "layer_norm_eps": 1e-05,
52
+ "length_penalty": 1.0,
53
+ "max_length": 20,
54
+ "max_position_embeddings": 77,
55
+ "min_length": 0,
56
+ "model_type": "xclip_text_model",
57
+ "no_repeat_ngram_size": 0,
58
+ "num_attention_heads": 8,
59
+ "num_beam_groups": 1,
60
+ "num_beams": 1,
61
+ "num_hidden_layers": 12,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": 1,
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "return_dict": true,
73
+ "return_dict_in_generate": false,
74
+ "sep_token_id": null,
75
+ "task_specific_params": null,
76
+ "temperature": 1.0,
77
+ "tf_legacy_loss": false,
78
+ "tie_encoder_decoder": false,
79
+ "tie_word_embeddings": true,
80
+ "tokenizer_class": null,
81
+ "top_k": 50,
82
+ "top_p": 1.0,
83
+ "torch_dtype": null,
84
+ "torchscript": false,
85
+ "transformers_version": "4.22.0.dev0",
86
+ "typical_p": 1.0,
87
+ "use_bfloat16": false,
88
+ "vocab_size": 49408
89
+ },
90
+ "text_config_dict": null,
91
+ "torch_dtype": "float32",
92
+ "transformers_version": null,
93
+ "vision_config": {
94
+ "_name_or_path": "",
95
+ "add_cross_attention": false,
96
+ "architectures": null,
97
+ "attention_dropout": 0.0,
98
+ "bad_words_ids": null,
99
+ "bos_token_id": null,
100
+ "chunk_size_feed_forward": 0,
101
+ "cross_attention_hidden_size": null,
102
+ "decoder_start_token_id": null,
103
+ "diversity_penalty": 0.0,
104
+ "do_sample": false,
105
+ "drop_path_rate": 0.0,
106
+ "dropout": 0.0,
107
+ "early_stopping": false,
108
+ "encoder_no_repeat_ngram_size": 0,
109
+ "eos_token_id": null,
110
+ "exponential_decay_length_penalty": null,
111
+ "finetuning_task": null,
112
+ "forced_bos_token_id": null,
113
+ "forced_eos_token_id": null,
114
+ "hidden_act": "quick_gelu",
115
+ "hidden_size": 768,
116
+ "id2label": {
117
+ "0": "LABEL_0",
118
+ "1": "LABEL_1"
119
+ },
120
+ "image_size": 224,
121
+ "initializer_factor": 1.0,
122
+ "initializer_range": 0.02,
123
+ "intermediate_size": 3072,
124
+ "is_decoder": false,
125
+ "is_encoder_decoder": false,
126
+ "label2id": {
127
+ "LABEL_0": 0,
128
+ "LABEL_1": 1
129
+ },
130
+ "layer_norm_eps": 1e-05,
131
+ "length_penalty": 1.0,
132
+ "max_length": 20,
133
+ "min_length": 0,
134
+ "mit_hidden_size": 512,
135
+ "mit_intermediate_size": 2048,
136
+ "mit_num_attention_heads": 8,
137
+ "mit_num_hidden_layers": 1,
138
+ "model_type": "xclip_vision_model",
139
+ "no_repeat_ngram_size": 0,
140
+ "num_attention_heads": 12,
141
+ "num_beam_groups": 1,
142
+ "num_beams": 1,
143
+ "num_channels": 3,
144
+ "num_frames": 8,
145
+ "num_hidden_layers": 12,
146
+ "num_return_sequences": 1,
147
+ "output_attentions": false,
148
+ "output_hidden_states": false,
149
+ "output_scores": false,
150
+ "pad_token_id": null,
151
+ "patch_size": 32,
152
+ "prefix": null,
153
+ "problem_type": null,
154
+ "pruned_heads": {},
155
+ "remove_invalid_values": false,
156
+ "repetition_penalty": 1.0,
157
+ "return_dict": true,
158
+ "return_dict_in_generate": false,
159
+ "sep_token_id": null,
160
+ "task_specific_params": null,
161
+ "temperature": 1.0,
162
+ "tf_legacy_loss": false,
163
+ "tie_encoder_decoder": false,
164
+ "tie_word_embeddings": true,
165
+ "tokenizer_class": null,
166
+ "top_k": 50,
167
+ "top_p": 1.0,
168
+ "torch_dtype": null,
169
+ "torchscript": false,
170
+ "transformers_version": "4.22.0.dev0",
171
+ "typical_p": 1.0,
172
+ "use_bfloat16": false
173
+ },
174
+ "vision_config_dict": null
175
+ }
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:abf286e8cdd0612761c3e42d3a55eca998382dfa67a04a0f3fdcdfa4f150cdbb
3
+ size 786414772
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_center_crop": true,
3
+ "do_normalize": true,
4
+ "do_resize": true,
5
+ "feature_extractor_type": "VideoMAEFeatureExtractor",
6
+ "image_mean": [
7
+ 0.485,
8
+ 0.456,
9
+ 0.406
10
+ ],
11
+ "image_std": [
12
+ 0.229,
13
+ 0.224,
14
+ 0.225
15
+ ],
16
+ "processor_class": "XCLIPProcessor",
17
+ "resample": 2,
18
+ "size": 224
19
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
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": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "do_lower_case": true,
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 77,
22
+ "name_or_path": "openai/clip-vit-base-patch32",
23
+ "pad_token": "<|endoftext|>",
24
+ "processor_class": "CLIPProcessor",
25
+ "special_tokens_map_file": "/home/niels/.cache/huggingface/hub/models--openai--clip-vit-base-patch32/snapshots/f4881ba48ee4d21b7ed5602603b9e3e92eb1b346/special_tokens_map.json",
26
+ "tokenizer_class": "CLIPTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff