Hugging Face's logo

jkrukowski
/
clip-vit-base-patch16

MLX
Safetensors
clip
Model card Files Community
Jan Krukowski commited on
Commit
0e271f4
·
1 Parent(s): 2074b9d

initial commit

Browse files
Files changed (7) hide show
  1. README.md +8 -0
  2. config.json +157 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. model.safetensors.index.json +407 -0
  6. preprocessor_config.json +19 -0
  7. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: mlx
4
+ ---
5
+
6
+ # mlx-community/clip-vit-base-patch16
7
+
8
+ [mlx-community/clip-vit-base-patch16](https://huggingface.co/mlx-community/clip-vit-base-patch16) converted to `safetensors` format.
config.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPModel"
4
+ ],
5
+ "initializer_factor": 1.0,
6
+ "logit_scale_init_value": 2.6592,
7
+ "model_type": "clip",
8
+ "projection_dim": 512,
9
+ "text_config": {
10
+ "_name_or_path": "",
11
+ "add_cross_attention": false,
12
+ "architectures": null,
13
+ "attention_dropout": 0.0,
14
+ "bad_words_ids": null,
15
+ "bos_token_id": 0,
16
+ "chunk_size_feed_forward": 0,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "dropout": 0.0,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": 2,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "quick_gelu",
28
+ "hidden_size": 512,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_factor": 1.0,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 2048,
36
+ "is_decoder": false,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 77,
46
+ "min_length": 0,
47
+ "model_type": "clip_text_model",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 8,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 1,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "projection_dim" : 512,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tie_encoder_decoder": false,
70
+ "tie_word_embeddings": true,
71
+ "tokenizer_class": null,
72
+ "top_k": 50,
73
+ "top_p": 1.0,
74
+ "torch_dtype": null,
75
+ "torchscript": false,
76
+ "transformers_version": "4.12.0.dev0",
77
+ "use_bfloat16": false,
78
+ "vocab_size": 49408
79
+ },
80
+ "text_config_dict": null,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": null,
83
+ "vision_config": {
84
+ "_name_or_path": "",
85
+ "add_cross_attention": false,
86
+ "architectures": null,
87
+ "attention_dropout": 0.0,
88
+ "bad_words_ids": null,
89
+ "bos_token_id": null,
90
+ "chunk_size_feed_forward": 0,
91
+ "decoder_start_token_id": null,
92
+ "diversity_penalty": 0.0,
93
+ "do_sample": false,
94
+ "dropout": 0.0,
95
+ "early_stopping": false,
96
+ "encoder_no_repeat_ngram_size": 0,
97
+ "eos_token_id": null,
98
+ "finetuning_task": null,
99
+ "forced_bos_token_id": null,
100
+ "forced_eos_token_id": null,
101
+ "hidden_act": "quick_gelu",
102
+ "hidden_size": 768,
103
+ "id2label": {
104
+ "0": "LABEL_0",
105
+ "1": "LABEL_1"
106
+ },
107
+ "image_size": 224,
108
+ "initializer_factor": 1.0,
109
+ "initializer_range": 0.02,
110
+ "intermediate_size": 3072,
111
+ "is_decoder": false,
112
+ "is_encoder_decoder": false,
113
+ "label2id": {
114
+ "LABEL_0": 0,
115
+ "LABEL_1": 1
116
+ },
117
+ "layer_norm_eps": 1e-05,
118
+ "length_penalty": 1.0,
119
+ "max_length": 20,
120
+ "min_length": 0,
121
+ "model_type": "clip_vision_model",
122
+ "no_repeat_ngram_size": 0,
123
+ "num_attention_heads": 12,
124
+ "num_beam_groups": 1,
125
+ "num_beams": 1,
126
+ "num_hidden_layers": 12,
127
+ "num_return_sequences": 1,
128
+ "output_attentions": false,
129
+ "output_hidden_states": false,
130
+ "output_scores": false,
131
+ "pad_token_id": null,
132
+ "patch_size": 16,
133
+ "prefix": null,
134
+ "problem_type": null,
135
+ "projection_dim" : 512,
136
+ "pruned_heads": {},
137
+ "remove_invalid_values": false,
138
+ "repetition_penalty": 1.0,
139
+ "return_dict": true,
140
+ "return_dict_in_generate": false,
141
+ "sep_token_id": null,
142
+ "task_specific_params": null,
143
+ "temperature": 1.0,
144
+ "tie_encoder_decoder": false,
145
+ "tie_word_embeddings": true,
146
+ "tokenizer_class": null,
147
+ "top_k": 50,
148
+ "top_p": 1.0,
149
+ "torch_dtype": null,
150
+ "torchscript": false,
151
+ "transformers_version": "4.12.0.dev0",
152
+ "use_bfloat16": false
153
+ },
154
+ "vision_config_dict": {
155
+ "patch_size": 16
156
+ }
157
+ }
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 sha256:231934b12eecfa5b110b05064c917ea9e3a14c26af4abe02d75ce5bf53dcbf25
3
+ size 598531510
model.safetensors.index.json ADDED
@@ -0,0 +1,407 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 598484044
4
+ },
5
+ "weight_map": {
6
+ "logit_scale": "model.safetensors",
7
+ "text_model.embeddings.position_embedding.weight": "model.safetensors",
8
+ "text_model.embeddings.position_ids": "model.safetensors",
9
+ "text_model.embeddings.token_embedding.weight": "model.safetensors",
10
+ "text_model.encoder.layers.0.layer_norm1.bias": "model.safetensors",
11
+ "text_model.encoder.layers.0.layer_norm1.weight": "model.safetensors",
12
+ "text_model.encoder.layers.0.layer_norm2.bias": "model.safetensors",
13
+ "text_model.encoder.layers.0.layer_norm2.weight": "model.safetensors",
14
+ "text_model.encoder.layers.0.mlp.fc1.bias": "model.safetensors",
15
+ "text_model.encoder.layers.0.mlp.fc1.weight": "model.safetensors",
16
+ "text_model.encoder.layers.0.mlp.fc2.bias": "model.safetensors",
17
+ "text_model.encoder.layers.0.mlp.fc2.weight": "model.safetensors",
18
+ "text_model.encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
19
+ "text_model.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
20
+ "text_model.encoder.layers.0.self_attn.out_proj.bias": "model.safetensors",
21
+ "text_model.encoder.layers.0.self_attn.out_proj.weight": "model.safetensors",
22
+ "text_model.encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
23
+ "text_model.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
24
+ "text_model.encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
25
+ "text_model.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
26
+ "text_model.encoder.layers.1.layer_norm1.bias": "model.safetensors",
27
+ "text_model.encoder.layers.1.layer_norm1.weight": "model.safetensors",
28
+ "text_model.encoder.layers.1.layer_norm2.bias": "model.safetensors",
29
+ "text_model.encoder.layers.1.layer_norm2.weight": "model.safetensors",
30
+ "text_model.encoder.layers.1.mlp.fc1.bias": "model.safetensors",
31
+ "text_model.encoder.layers.1.mlp.fc1.weight": "model.safetensors",
32
+ "text_model.encoder.layers.1.mlp.fc2.bias": "model.safetensors",
33
+ "text_model.encoder.layers.1.mlp.fc2.weight": "model.safetensors",
34
+ "text_model.encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
35
+ "text_model.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
36
+ "text_model.encoder.layers.1.self_attn.out_proj.bias": "model.safetensors",
37
+ "text_model.encoder.layers.1.self_attn.out_proj.weight": "model.safetensors",
38
+ "text_model.encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
39
+ "text_model.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
40
+ "text_model.encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
41
+ "text_model.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
42
+ "text_model.encoder.layers.10.layer_norm1.bias": "model.safetensors",
43
+ "text_model.encoder.layers.10.layer_norm1.weight": "model.safetensors",
44
+ "text_model.encoder.layers.10.layer_norm2.bias": "model.safetensors",
45
+ "text_model.encoder.layers.10.layer_norm2.weight": "model.safetensors",
46
+ "text_model.encoder.layers.10.mlp.fc1.bias": "model.safetensors",
47
+ "text_model.encoder.layers.10.mlp.fc1.weight": "model.safetensors",
48
+ "text_model.encoder.layers.10.mlp.fc2.bias": "model.safetensors",
49
+ "text_model.encoder.layers.10.mlp.fc2.weight": "model.safetensors",
50
+ "text_model.encoder.layers.10.self_attn.k_proj.bias": "model.safetensors",
51
+ "text_model.encoder.layers.10.self_attn.k_proj.weight": "model.safetensors",
52
+ "text_model.encoder.layers.10.self_attn.out_proj.bias": "model.safetensors",
53
+ "text_model.encoder.layers.10.self_attn.out_proj.weight": "model.safetensors",
54
+ "text_model.encoder.layers.10.self_attn.q_proj.bias": "model.safetensors",
55
+ "text_model.encoder.layers.10.self_attn.q_proj.weight": "model.safetensors",
56
+ "text_model.encoder.layers.10.self_attn.v_proj.bias": "model.safetensors",
57
+ "text_model.encoder.layers.10.self_attn.v_proj.weight": "model.safetensors",
58
+ "text_model.encoder.layers.11.layer_norm1.bias": "model.safetensors",
59
+ "text_model.encoder.layers.11.layer_norm1.weight": "model.safetensors",
60
+ "text_model.encoder.layers.11.layer_norm2.bias": "model.safetensors",
61
+ "text_model.encoder.layers.11.layer_norm2.weight": "model.safetensors",
62
+ "text_model.encoder.layers.11.mlp.fc1.bias": "model.safetensors",
63
+ "text_model.encoder.layers.11.mlp.fc1.weight": "model.safetensors",
64
+ "text_model.encoder.layers.11.mlp.fc2.bias": "model.safetensors",
65
+ "text_model.encoder.layers.11.mlp.fc2.weight": "model.safetensors",
66
+ "text_model.encoder.layers.11.self_attn.k_proj.bias": "model.safetensors",
67
+ "text_model.encoder.layers.11.self_attn.k_proj.weight": "model.safetensors",
68
+ "text_model.encoder.layers.11.self_attn.out_proj.bias": "model.safetensors",
69
+ "text_model.encoder.layers.11.self_attn.out_proj.weight": "model.safetensors",
70
+ "text_model.encoder.layers.11.self_attn.q_proj.bias": "model.safetensors",
71
+ "text_model.encoder.layers.11.self_attn.q_proj.weight": "model.safetensors",
72
+ "text_model.encoder.layers.11.self_attn.v_proj.bias": "model.safetensors",
73
+ "text_model.encoder.layers.11.self_attn.v_proj.weight": "model.safetensors",
74
+ "text_model.encoder.layers.2.layer_norm1.bias": "model.safetensors",
75
+ "text_model.encoder.layers.2.layer_norm1.weight": "model.safetensors",
76
+ "text_model.encoder.layers.2.layer_norm2.bias": "model.safetensors",
77
+ "text_model.encoder.layers.2.layer_norm2.weight": "model.safetensors",
78
+ "text_model.encoder.layers.2.mlp.fc1.bias": "model.safetensors",
79
+ "text_model.encoder.layers.2.mlp.fc1.weight": "model.safetensors",
80
+ "text_model.encoder.layers.2.mlp.fc2.bias": "model.safetensors",
81
+ "text_model.encoder.layers.2.mlp.fc2.weight": "model.safetensors",
82
+ "text_model.encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
83
+ "text_model.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
84
+ "text_model.encoder.layers.2.self_attn.out_proj.bias": "model.safetensors",
85
+ "text_model.encoder.layers.2.self_attn.out_proj.weight": "model.safetensors",
86
+ "text_model.encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
87
+ "text_model.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
88
+ "text_model.encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
89
+ "text_model.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
90
+ "text_model.encoder.layers.3.layer_norm1.bias": "model.safetensors",
91
+ "text_model.encoder.layers.3.layer_norm1.weight": "model.safetensors",
92
+ "text_model.encoder.layers.3.layer_norm2.bias": "model.safetensors",
93
+ "text_model.encoder.layers.3.layer_norm2.weight": "model.safetensors",
94
+ "text_model.encoder.layers.3.mlp.fc1.bias": "model.safetensors",
95
+ "text_model.encoder.layers.3.mlp.fc1.weight": "model.safetensors",
96
+ "text_model.encoder.layers.3.mlp.fc2.bias": "model.safetensors",
97
+ "text_model.encoder.layers.3.mlp.fc2.weight": "model.safetensors",
98
+ "text_model.encoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
99
+ "text_model.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
100
+ "text_model.encoder.layers.3.self_attn.out_proj.bias": "model.safetensors",
101
+ "text_model.encoder.layers.3.self_attn.out_proj.weight": "model.safetensors",
102
+ "text_model.encoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
103
+ "text_model.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
104
+ "text_model.encoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
105
+ "text_model.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
106
+ "text_model.encoder.layers.4.layer_norm1.bias": "model.safetensors",
107
+ "text_model.encoder.layers.4.layer_norm1.weight": "model.safetensors",
108
+ "text_model.encoder.layers.4.layer_norm2.bias": "model.safetensors",
109
+ "text_model.encoder.layers.4.layer_norm2.weight": "model.safetensors",
110
+ "text_model.encoder.layers.4.mlp.fc1.bias": "model.safetensors",
111
+ "text_model.encoder.layers.4.mlp.fc1.weight": "model.safetensors",
112
+ "text_model.encoder.layers.4.mlp.fc2.bias": "model.safetensors",
113
+ "text_model.encoder.layers.4.mlp.fc2.weight": "model.safetensors",
114
+ "text_model.encoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
115
+ "text_model.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
116
+ "text_model.encoder.layers.4.self_attn.out_proj.bias": "model.safetensors",
117
+ "text_model.encoder.layers.4.self_attn.out_proj.weight": "model.safetensors",
118
+ "text_model.encoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
119
+ "text_model.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
120
+ "text_model.encoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
121
+ "text_model.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
122
+ "text_model.encoder.layers.5.layer_norm1.bias": "model.safetensors",
123
+ "text_model.encoder.layers.5.layer_norm1.weight": "model.safetensors",
124
+ "text_model.encoder.layers.5.layer_norm2.bias": "model.safetensors",
125
+ "text_model.encoder.layers.5.layer_norm2.weight": "model.safetensors",
126
+ "text_model.encoder.layers.5.mlp.fc1.bias": "model.safetensors",
127
+ "text_model.encoder.layers.5.mlp.fc1.weight": "model.safetensors",
128
+ "text_model.encoder.layers.5.mlp.fc2.bias": "model.safetensors",
129
+ "text_model.encoder.layers.5.mlp.fc2.weight": "model.safetensors",
130
+ "text_model.encoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
131
+ "text_model.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
132
+ "text_model.encoder.layers.5.self_attn.out_proj.bias": "model.safetensors",
133
+ "text_model.encoder.layers.5.self_attn.out_proj.weight": "model.safetensors",
134
+ "text_model.encoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
135
+ "text_model.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
136
+ "text_model.encoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
137
+ "text_model.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
138
+ "text_model.encoder.layers.6.layer_norm1.bias": "model.safetensors",
139
+ "text_model.encoder.layers.6.layer_norm1.weight": "model.safetensors",
140
+ "text_model.encoder.layers.6.layer_norm2.bias": "model.safetensors",
141
+ "text_model.encoder.layers.6.layer_norm2.weight": "model.safetensors",
142
+ "text_model.encoder.layers.6.mlp.fc1.bias": "model.safetensors",
143
+ "text_model.encoder.layers.6.mlp.fc1.weight": "model.safetensors",
144
+ "text_model.encoder.layers.6.mlp.fc2.bias": "model.safetensors",
145
+ "text_model.encoder.layers.6.mlp.fc2.weight": "model.safetensors",
146
+ "text_model.encoder.layers.6.self_attn.k_proj.bias": "model.safetensors",
147
+ "text_model.encoder.layers.6.self_attn.k_proj.weight": "model.safetensors",
148
+ "text_model.encoder.layers.6.self_attn.out_proj.bias": "model.safetensors",
149
+ "text_model.encoder.layers.6.self_attn.out_proj.weight": "model.safetensors",
150
+ "text_model.encoder.layers.6.self_attn.q_proj.bias": "model.safetensors",
151
+ "text_model.encoder.layers.6.self_attn.q_proj.weight": "model.safetensors",
152
+ "text_model.encoder.layers.6.self_attn.v_proj.bias": "model.safetensors",
153
+ "text_model.encoder.layers.6.self_attn.v_proj.weight": "model.safetensors",
154
+ "text_model.encoder.layers.7.layer_norm1.bias": "model.safetensors",
155
+ "text_model.encoder.layers.7.layer_norm1.weight": "model.safetensors",
156
+ "text_model.encoder.layers.7.layer_norm2.bias": "model.safetensors",
157
+ "text_model.encoder.layers.7.layer_norm2.weight": "model.safetensors",
158
+ "text_model.encoder.layers.7.mlp.fc1.bias": "model.safetensors",
159
+ "text_model.encoder.layers.7.mlp.fc1.weight": "model.safetensors",
160
+ "text_model.encoder.layers.7.mlp.fc2.bias": "model.safetensors",
161
+ "text_model.encoder.layers.7.mlp.fc2.weight": "model.safetensors",
162
+ "text_model.encoder.layers.7.self_attn.k_proj.bias": "model.safetensors",
163
+ "text_model.encoder.layers.7.self_attn.k_proj.weight": "model.safetensors",
164
+ "text_model.encoder.layers.7.self_attn.out_proj.bias": "model.safetensors",
165
+ "text_model.encoder.layers.7.self_attn.out_proj.weight": "model.safetensors",
166
+ "text_model.encoder.layers.7.self_attn.q_proj.bias": "model.safetensors",
167
+ "text_model.encoder.layers.7.self_attn.q_proj.weight": "model.safetensors",
168
+ "text_model.encoder.layers.7.self_attn.v_proj.bias": "model.safetensors",
169
+ "text_model.encoder.layers.7.self_attn.v_proj.weight": "model.safetensors",
170
+ "text_model.encoder.layers.8.layer_norm1.bias": "model.safetensors",
171
+ "text_model.encoder.layers.8.layer_norm1.weight": "model.safetensors",
172
+ "text_model.encoder.layers.8.layer_norm2.bias": "model.safetensors",
173
+ "text_model.encoder.layers.8.layer_norm2.weight": "model.safetensors",
174
+ "text_model.encoder.layers.8.mlp.fc1.bias": "model.safetensors",
175
+ "text_model.encoder.layers.8.mlp.fc1.weight": "model.safetensors",
176
+ "text_model.encoder.layers.8.mlp.fc2.bias": "model.safetensors",
177
+ "text_model.encoder.layers.8.mlp.fc2.weight": "model.safetensors",
178
+ "text_model.encoder.layers.8.self_attn.k_proj.bias": "model.safetensors",
179
+ "text_model.encoder.layers.8.self_attn.k_proj.weight": "model.safetensors",
180
+ "text_model.encoder.layers.8.self_attn.out_proj.bias": "model.safetensors",
181
+ "text_model.encoder.layers.8.self_attn.out_proj.weight": "model.safetensors",
182
+ "text_model.encoder.layers.8.self_attn.q_proj.bias": "model.safetensors",
183
+ "text_model.encoder.layers.8.self_attn.q_proj.weight": "model.safetensors",
184
+ "text_model.encoder.layers.8.self_attn.v_proj.bias": "model.safetensors",
185
+ "text_model.encoder.layers.8.self_attn.v_proj.weight": "model.safetensors",
186
+ "text_model.encoder.layers.9.layer_norm1.bias": "model.safetensors",
187
+ "text_model.encoder.layers.9.layer_norm1.weight": "model.safetensors",
188
+ "text_model.encoder.layers.9.layer_norm2.bias": "model.safetensors",
189
+ "text_model.encoder.layers.9.layer_norm2.weight": "model.safetensors",
190
+ "text_model.encoder.layers.9.mlp.fc1.bias": "model.safetensors",
191
+ "text_model.encoder.layers.9.mlp.fc1.weight": "model.safetensors",
192
+ "text_model.encoder.layers.9.mlp.fc2.bias": "model.safetensors",
193
+ "text_model.encoder.layers.9.mlp.fc2.weight": "model.safetensors",
194
+ "text_model.encoder.layers.9.self_attn.k_proj.bias": "model.safetensors",
195
+ "text_model.encoder.layers.9.self_attn.k_proj.weight": "model.safetensors",
196
+ "text_model.encoder.layers.9.self_attn.out_proj.bias": "model.safetensors",
197
+ "text_model.encoder.layers.9.self_attn.out_proj.weight": "model.safetensors",
198
+ "text_model.encoder.layers.9.self_attn.q_proj.bias": "model.safetensors",
199
+ "text_model.encoder.layers.9.self_attn.q_proj.weight": "model.safetensors",
200
+ "text_model.encoder.layers.9.self_attn.v_proj.bias": "model.safetensors",
201
+ "text_model.encoder.layers.9.self_attn.v_proj.weight": "model.safetensors",
202
+ "text_model.final_layer_norm.bias": "model.safetensors",
203
+ "text_model.final_layer_norm.weight": "model.safetensors",
204
+ "text_projection.weight": "model.safetensors",
205
+ "vision_model.embeddings.class_embedding": "model.safetensors",
206
+ "vision_model.embeddings.patch_embedding.weight": "model.safetensors",
207
+ "vision_model.embeddings.position_embedding.weight": "model.safetensors",
208
+ "vision_model.embeddings.position_ids": "model.safetensors",
209
+ "vision_model.encoder.layers.0.layer_norm1.bias": "model.safetensors",
210
+ "vision_model.encoder.layers.0.layer_norm1.weight": "model.safetensors",
211
+ "vision_model.encoder.layers.0.layer_norm2.bias": "model.safetensors",
212
+ "vision_model.encoder.layers.0.layer_norm2.weight": "model.safetensors",
213
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model.safetensors",
214
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model.safetensors",
215
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model.safetensors",
216
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model.safetensors",
217
+ "vision_model.encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
218
+ "vision_model.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
219
+ "vision_model.encoder.layers.0.self_attn.out_proj.bias": "model.safetensors",
220
+ "vision_model.encoder.layers.0.self_attn.out_proj.weight": "model.safetensors",
221
+ "vision_model.encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
222
+ "vision_model.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
223
+ "vision_model.encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
224
+ "vision_model.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
225
+ "vision_model.encoder.layers.1.layer_norm1.bias": "model.safetensors",
226
+ "vision_model.encoder.layers.1.layer_norm1.weight": "model.safetensors",
227
+ "vision_model.encoder.layers.1.layer_norm2.bias": "model.safetensors",
228
+ "vision_model.encoder.layers.1.layer_norm2.weight": "model.safetensors",
229
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model.safetensors",
230
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model.safetensors",
231
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model.safetensors",
232
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model.safetensors",
233
+ "vision_model.encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
234
+ "vision_model.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
235
+ "vision_model.encoder.layers.1.self_attn.out_proj.bias": "model.safetensors",
236
+ "vision_model.encoder.layers.1.self_attn.out_proj.weight": "model.safetensors",
237
+ "vision_model.encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
238
+ "vision_model.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
239
+ "vision_model.encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
240
+ "vision_model.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
241
+ "vision_model.encoder.layers.10.layer_norm1.bias": "model.safetensors",
242
+ "vision_model.encoder.layers.10.layer_norm1.weight": "model.safetensors",
243
+ "vision_model.encoder.layers.10.layer_norm2.bias": "model.safetensors",
244
+ "vision_model.encoder.layers.10.layer_norm2.weight": "model.safetensors",
245
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model.safetensors",
246
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model.safetensors",
247
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model.safetensors",
248
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model.safetensors",
249
+ "vision_model.encoder.layers.10.self_attn.k_proj.bias": "model.safetensors",
250
+ "vision_model.encoder.layers.10.self_attn.k_proj.weight": "model.safetensors",
251
+ "vision_model.encoder.layers.10.self_attn.out_proj.bias": "model.safetensors",
252
+ "vision_model.encoder.layers.10.self_attn.out_proj.weight": "model.safetensors",
253
+ "vision_model.encoder.layers.10.self_attn.q_proj.bias": "model.safetensors",
254
+ "vision_model.encoder.layers.10.self_attn.q_proj.weight": "model.safetensors",
255
+ "vision_model.encoder.layers.10.self_attn.v_proj.bias": "model.safetensors",
256
+ "vision_model.encoder.layers.10.self_attn.v_proj.weight": "model.safetensors",
257
+ "vision_model.encoder.layers.11.layer_norm1.bias": "model.safetensors",
258
+ "vision_model.encoder.layers.11.layer_norm1.weight": "model.safetensors",
259
+ "vision_model.encoder.layers.11.layer_norm2.bias": "model.safetensors",
260
+ "vision_model.encoder.layers.11.layer_norm2.weight": "model.safetensors",
261
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model.safetensors",
262
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model.safetensors",
263
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model.safetensors",
264
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model.safetensors",
265
+ "vision_model.encoder.layers.11.self_attn.k_proj.bias": "model.safetensors",
266
+ "vision_model.encoder.layers.11.self_attn.k_proj.weight": "model.safetensors",
267
+ "vision_model.encoder.layers.11.self_attn.out_proj.bias": "model.safetensors",
268
+ "vision_model.encoder.layers.11.self_attn.out_proj.weight": "model.safetensors",
269
+ "vision_model.encoder.layers.11.self_attn.q_proj.bias": "model.safetensors",
270
+ "vision_model.encoder.layers.11.self_attn.q_proj.weight": "model.safetensors",
271
+ "vision_model.encoder.layers.11.self_attn.v_proj.bias": "model.safetensors",
272
+ "vision_model.encoder.layers.11.self_attn.v_proj.weight": "model.safetensors",
273
+ "vision_model.encoder.layers.2.layer_norm1.bias": "model.safetensors",
274
+ "vision_model.encoder.layers.2.layer_norm1.weight": "model.safetensors",
275
+ "vision_model.encoder.layers.2.layer_norm2.bias": "model.safetensors",
276
+ "vision_model.encoder.layers.2.layer_norm2.weight": "model.safetensors",
277
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model.safetensors",
278
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model.safetensors",
279
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model.safetensors",
280
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model.safetensors",
281
+ "vision_model.encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
282
+ "vision_model.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
283
+ "vision_model.encoder.layers.2.self_attn.out_proj.bias": "model.safetensors",
284
+ "vision_model.encoder.layers.2.self_attn.out_proj.weight": "model.safetensors",
285
+ "vision_model.encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
286
+ "vision_model.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
287
+ "vision_model.encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
288
+ "vision_model.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
289
+ "vision_model.encoder.layers.3.layer_norm1.bias": "model.safetensors",
290
+ "vision_model.encoder.layers.3.layer_norm1.weight": "model.safetensors",
291
+ "vision_model.encoder.layers.3.layer_norm2.bias": "model.safetensors",
292
+ "vision_model.encoder.layers.3.layer_norm2.weight": "model.safetensors",
293
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model.safetensors",
294
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model.safetensors",
295
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model.safetensors",
296
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model.safetensors",
297
+ "vision_model.encoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
298
+ "vision_model.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
299
+ "vision_model.encoder.layers.3.self_attn.out_proj.bias": "model.safetensors",
300
+ "vision_model.encoder.layers.3.self_attn.out_proj.weight": "model.safetensors",
301
+ "vision_model.encoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
302
+ "vision_model.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
303
+ "vision_model.encoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
304
+ "vision_model.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
305
+ "vision_model.encoder.layers.4.layer_norm1.bias": "model.safetensors",
306
+ "vision_model.encoder.layers.4.layer_norm1.weight": "model.safetensors",
307
+ "vision_model.encoder.layers.4.layer_norm2.bias": "model.safetensors",
308
+ "vision_model.encoder.layers.4.layer_norm2.weight": "model.safetensors",
309
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model.safetensors",
310
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model.safetensors",
311
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model.safetensors",
312
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model.safetensors",
313
+ "vision_model.encoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
314
+ "vision_model.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
315
+ "vision_model.encoder.layers.4.self_attn.out_proj.bias": "model.safetensors",
316
+ "vision_model.encoder.layers.4.self_attn.out_proj.weight": "model.safetensors",
317
+ "vision_model.encoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
318
+ "vision_model.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
319
+ "vision_model.encoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
320
+ "vision_model.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
321
+ "vision_model.encoder.layers.5.layer_norm1.bias": "model.safetensors",
322
+ "vision_model.encoder.layers.5.layer_norm1.weight": "model.safetensors",
323
+ "vision_model.encoder.layers.5.layer_norm2.bias": "model.safetensors",
324
+ "vision_model.encoder.layers.5.layer_norm2.weight": "model.safetensors",
325
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model.safetensors",
326
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model.safetensors",
327
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model.safetensors",
328
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model.safetensors",
329
+ "vision_model.encoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
330
+ "vision_model.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
331
+ "vision_model.encoder.layers.5.self_attn.out_proj.bias": "model.safetensors",
332
+ "vision_model.encoder.layers.5.self_attn.out_proj.weight": "model.safetensors",
333
+ "vision_model.encoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
334
+ "vision_model.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
335
+ "vision_model.encoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
336
+ "vision_model.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
337
+ "vision_model.encoder.layers.6.layer_norm1.bias": "model.safetensors",
338
+ "vision_model.encoder.layers.6.layer_norm1.weight": "model.safetensors",
339
+ "vision_model.encoder.layers.6.layer_norm2.bias": "model.safetensors",
340
+ "vision_model.encoder.layers.6.layer_norm2.weight": "model.safetensors",
341
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model.safetensors",
342
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model.safetensors",
343
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model.safetensors",
344
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model.safetensors",
345
+ "vision_model.encoder.layers.6.self_attn.k_proj.bias": "model.safetensors",
346
+ "vision_model.encoder.layers.6.self_attn.k_proj.weight": "model.safetensors",
347
+ "vision_model.encoder.layers.6.self_attn.out_proj.bias": "model.safetensors",
348
+ "vision_model.encoder.layers.6.self_attn.out_proj.weight": "model.safetensors",
349
+ "vision_model.encoder.layers.6.self_attn.q_proj.bias": "model.safetensors",
350
+ "vision_model.encoder.layers.6.self_attn.q_proj.weight": "model.safetensors",
351
+ "vision_model.encoder.layers.6.self_attn.v_proj.bias": "model.safetensors",
352
+ "vision_model.encoder.layers.6.self_attn.v_proj.weight": "model.safetensors",
353
+ "vision_model.encoder.layers.7.layer_norm1.bias": "model.safetensors",
354
+ "vision_model.encoder.layers.7.layer_norm1.weight": "model.safetensors",
355
+ "vision_model.encoder.layers.7.layer_norm2.bias": "model.safetensors",
356
+ "vision_model.encoder.layers.7.layer_norm2.weight": "model.safetensors",
357
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model.safetensors",
358
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model.safetensors",
359
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model.safetensors",
360
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model.safetensors",
361
+ "vision_model.encoder.layers.7.self_attn.k_proj.bias": "model.safetensors",
362
+ "vision_model.encoder.layers.7.self_attn.k_proj.weight": "model.safetensors",
363
+ "vision_model.encoder.layers.7.self_attn.out_proj.bias": "model.safetensors",
364
+ "vision_model.encoder.layers.7.self_attn.out_proj.weight": "model.safetensors",
365
+ "vision_model.encoder.layers.7.self_attn.q_proj.bias": "model.safetensors",
366
+ "vision_model.encoder.layers.7.self_attn.q_proj.weight": "model.safetensors",
367
+ "vision_model.encoder.layers.7.self_attn.v_proj.bias": "model.safetensors",
368
+ "vision_model.encoder.layers.7.self_attn.v_proj.weight": "model.safetensors",
369
+ "vision_model.encoder.layers.8.layer_norm1.bias": "model.safetensors",
370
+ "vision_model.encoder.layers.8.layer_norm1.weight": "model.safetensors",
371
+ "vision_model.encoder.layers.8.layer_norm2.bias": "model.safetensors",
372
+ "vision_model.encoder.layers.8.layer_norm2.weight": "model.safetensors",
373
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model.safetensors",
374
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model.safetensors",
375
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model.safetensors",
376
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model.safetensors",
377
+ "vision_model.encoder.layers.8.self_attn.k_proj.bias": "model.safetensors",
378
+ "vision_model.encoder.layers.8.self_attn.k_proj.weight": "model.safetensors",
379
+ "vision_model.encoder.layers.8.self_attn.out_proj.bias": "model.safetensors",
380
+ "vision_model.encoder.layers.8.self_attn.out_proj.weight": "model.safetensors",
381
+ "vision_model.encoder.layers.8.self_attn.q_proj.bias": "model.safetensors",
382
+ "vision_model.encoder.layers.8.self_attn.q_proj.weight": "model.safetensors",
383
+ "vision_model.encoder.layers.8.self_attn.v_proj.bias": "model.safetensors",
384
+ "vision_model.encoder.layers.8.self_attn.v_proj.weight": "model.safetensors",
385
+ "vision_model.encoder.layers.9.layer_norm1.bias": "model.safetensors",
386
+ "vision_model.encoder.layers.9.layer_norm1.weight": "model.safetensors",
387
+ "vision_model.encoder.layers.9.layer_norm2.bias": "model.safetensors",
388
+ "vision_model.encoder.layers.9.layer_norm2.weight": "model.safetensors",
389
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model.safetensors",
390
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model.safetensors",
391
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model.safetensors",
392
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model.safetensors",
393
+ "vision_model.encoder.layers.9.self_attn.k_proj.bias": "model.safetensors",
394
+ "vision_model.encoder.layers.9.self_attn.k_proj.weight": "model.safetensors",
395
+ "vision_model.encoder.layers.9.self_attn.out_proj.bias": "model.safetensors",
396
+ "vision_model.encoder.layers.9.self_attn.out_proj.weight": "model.safetensors",
397
+ "vision_model.encoder.layers.9.self_attn.q_proj.bias": "model.safetensors",
398
+ "vision_model.encoder.layers.9.self_attn.q_proj.weight": "model.safetensors",
399
+ "vision_model.encoder.layers.9.self_attn.v_proj.bias": "model.safetensors",
400
+ "vision_model.encoder.layers.9.self_attn.v_proj.weight": "model.safetensors",
401
+ "vision_model.post_layernorm.bias": "model.safetensors",
402
+ "vision_model.post_layernorm.weight": "model.safetensors",
403
+ "vision_model.pre_layrnorm.bias": "model.safetensors",
404
+ "vision_model.pre_layrnorm.weight": "model.safetensors",
405
+ "visual_projection.weight": "model.safetensors"
406
+ }
407
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 224,
3
+ "do_center_crop": true,
4
+ "do_normalize": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "CLIPFeatureExtractor",
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "resample": 3,
18
+ "size": 224
19
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff