Hugging Face's logo

sosoai
/
sam-vit-base-mlx

Mask Generation
Transformers
Safetensors
sam
Inference Endpoints
Model card Files Community
sosoai commited on
Commit
d782d8d
•
1 Parent(s): b221f64

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +249 -0
  2. model.safetensors +3 -0
  3. model.safetensors.index.json +321 -0
config.json ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/tmp/facebook/sam-vit-base",
4
+ "architectures": [
5
+ "SamModel"
6
+ ],
7
+ "initializer_range": 0.02,
8
+ "mask_decoder_config": {
9
+ "_name_or_path": "",
10
+ "add_cross_attention": false,
11
+ "architectures": null,
12
+ "attention_downsample_rate": 2,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": null,
16
+ "chunk_size_feed_forward": 0,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": null,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "hidden_act": "relu",
29
+ "hidden_size": 256,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "iou_head_depth": 3,
35
+ "iou_head_hidden_dim": 256,
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-06,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "min_length": 0,
46
+ "mlp_dim": 2048,
47
+ "model_type": "",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 8,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 2,
53
+ "num_multimask_outputs": 3,
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
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "suppress_tokens": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tf_legacy_loss": false,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "transformers_version": "4.29.0.dev0",
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false
81
+ },
82
+ "model_type": "sam",
83
+ "prompt_encoder_config": {
84
+ "_name_or_path": "",
85
+ "add_cross_attention": false,
86
+ "architectures": null,
87
+ "bad_words_ids": null,
88
+ "begin_suppress_tokens": null,
89
+ "bos_token_id": null,
90
+ "chunk_size_feed_forward": 0,
91
+ "cross_attention_hidden_size": null,
92
+ "decoder_start_token_id": null,
93
+ "diversity_penalty": 0.0,
94
+ "do_sample": false,
95
+ "early_stopping": false,
96
+ "encoder_no_repeat_ngram_size": 0,
97
+ "eos_token_id": null,
98
+ "exponential_decay_length_penalty": null,
99
+ "finetuning_task": null,
100
+ "forced_bos_token_id": null,
101
+ "forced_eos_token_id": null,
102
+ "hidden_act": "gelu",
103
+ "hidden_size": 256,
104
+ "id2label": {
105
+ "0": "LABEL_0",
106
+ "1": "LABEL_1"
107
+ },
108
+ "image_embedding_size": 64,
109
+ "image_size": 1024,
110
+ "is_decoder": false,
111
+ "is_encoder_decoder": false,
112
+ "label2id": {
113
+ "LABEL_0": 0,
114
+ "LABEL_1": 1
115
+ },
116
+ "layer_norm_eps": 1e-06,
117
+ "length_penalty": 1.0,
118
+ "mask_input_channels": 16,
119
+ "max_length": 20,
120
+ "min_length": 0,
121
+ "model_type": "",
122
+ "no_repeat_ngram_size": 0,
123
+ "num_beam_groups": 1,
124
+ "num_beams": 1,
125
+ "num_point_embeddings": 4,
126
+ "num_return_sequences": 1,
127
+ "output_attentions": false,
128
+ "output_hidden_states": false,
129
+ "output_scores": false,
130
+ "pad_token_id": null,
131
+ "patch_size": 16,
132
+ "prefix": null,
133
+ "problem_type": null,
134
+ "pruned_heads": {},
135
+ "remove_invalid_values": false,
136
+ "repetition_penalty": 1.0,
137
+ "return_dict": true,
138
+ "return_dict_in_generate": false,
139
+ "sep_token_id": null,
140
+ "suppress_tokens": null,
141
+ "task_specific_params": null,
142
+ "temperature": 1.0,
143
+ "tf_legacy_loss": false,
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": "4.29.0.dev0",
152
+ "typical_p": 1.0,
153
+ "use_bfloat16": false
154
+ },
155
+ "torch_dtype": "float32",
156
+ "transformers_version": null,
157
+ "vision_config": {
158
+ "_name_or_path": "",
159
+ "add_cross_attention": false,
160
+ "architectures": null,
161
+ "attention_dropout": 0.0,
162
+ "bad_words_ids": null,
163
+ "begin_suppress_tokens": null,
164
+ "bos_token_id": null,
165
+ "chunk_size_feed_forward": 0,
166
+ "cross_attention_hidden_size": null,
167
+ "decoder_start_token_id": null,
168
+ "diversity_penalty": 0.0,
169
+ "do_sample": false,
170
+ "dropout": 0.0,
171
+ "early_stopping": false,
172
+ "encoder_no_repeat_ngram_size": 0,
173
+ "eos_token_id": null,
174
+ "exponential_decay_length_penalty": null,
175
+ "finetuning_task": null,
176
+ "forced_bos_token_id": null,
177
+ "forced_eos_token_id": null,
178
+ "global_attn_indexes": [
179
+ 2,
180
+ 5,
181
+ 8,
182
+ 11
183
+ ],
184
+ "hidden_act": "gelu",
185
+ "hidden_size": 768,
186
+ "id2label": {
187
+ "0": "LABEL_0",
188
+ "1": "LABEL_1"
189
+ },
190
+ "image_size": 1024,
191
+ "initializer_factor": 1.0,
192
+ "initializer_range": 1e-10,
193
+ "intermediate_size": 6144,
194
+ "is_decoder": false,
195
+ "is_encoder_decoder": false,
196
+ "label2id": {
197
+ "LABEL_0": 0,
198
+ "LABEL_1": 1
199
+ },
200
+ "layer_norm_eps": 1e-06,
201
+ "length_penalty": 1.0,
202
+ "max_length": 20,
203
+ "min_length": 0,
204
+ "mlp_dim": 3072,
205
+ "mlp_ratio": 4.0,
206
+ "model_type": "",
207
+ "no_repeat_ngram_size": 0,
208
+ "num_attention_heads": 12,
209
+ "num_beam_groups": 1,
210
+ "num_beams": 1,
211
+ "num_channels": 3,
212
+ "num_hidden_layers": 12,
213
+ "num_pos_feats": 128,
214
+ "num_return_sequences": 1,
215
+ "output_attentions": false,
216
+ "output_channels": 256,
217
+ "output_hidden_states": false,
218
+ "output_scores": false,
219
+ "pad_token_id": null,
220
+ "patch_size": 16,
221
+ "prefix": null,
222
+ "problem_type": null,
223
+ "projection_dim": 512,
224
+ "pruned_heads": {},
225
+ "qkv_bias": true,
226
+ "remove_invalid_values": false,
227
+ "repetition_penalty": 1.0,
228
+ "return_dict": true,
229
+ "return_dict_in_generate": false,
230
+ "sep_token_id": null,
231
+ "suppress_tokens": null,
232
+ "task_specific_params": null,
233
+ "temperature": 1.0,
234
+ "tf_legacy_loss": false,
235
+ "tie_encoder_decoder": false,
236
+ "tie_word_embeddings": true,
237
+ "tokenizer_class": null,
238
+ "top_k": 50,
239
+ "top_p": 1.0,
240
+ "torch_dtype": null,
241
+ "torchscript": false,
242
+ "transformers_version": "4.29.0.dev0",
243
+ "typical_p": 1.0,
244
+ "use_abs_pos": true,
245
+ "use_bfloat16": false,
246
+ "use_rel_pos": true,
247
+ "window_size": 14
248
+ }
249
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6db9cdad0e7795caf18314d9b0a5bbd9017e8077c152b3a8bdf8ad11ecb241cb
3
+ size 374979608
model.safetensors.index.json ADDED
@@ -0,0 +1,321 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 374942912
4
+ },
5
+ "weight_map": {
6
+ "mask_decoder.iou_prediction_head.layers.0.bias": "model.safetensors",
7
+ "mask_decoder.iou_prediction_head.layers.0.weight": "model.safetensors",
8
+ "mask_decoder.iou_prediction_head.proj_in.bias": "model.safetensors",
9
+ "mask_decoder.iou_prediction_head.proj_in.weight": "model.safetensors",
10
+ "mask_decoder.iou_prediction_head.proj_out.bias": "model.safetensors",
11
+ "mask_decoder.iou_prediction_head.proj_out.weight": "model.safetensors",
12
+ "mask_decoder.iou_token.weight": "model.safetensors",
13
+ "mask_decoder.mask_tokens.weight": "model.safetensors",
14
+ "mask_decoder.output_hypernetworks_mlps.0.layers.0.bias": "model.safetensors",
15
+ "mask_decoder.output_hypernetworks_mlps.0.layers.0.weight": "model.safetensors",
16
+ "mask_decoder.output_hypernetworks_mlps.0.proj_in.bias": "model.safetensors",
17
+ "mask_decoder.output_hypernetworks_mlps.0.proj_in.weight": "model.safetensors",
18
+ "mask_decoder.output_hypernetworks_mlps.0.proj_out.bias": "model.safetensors",
19
+ "mask_decoder.output_hypernetworks_mlps.0.proj_out.weight": "model.safetensors",
20
+ "mask_decoder.output_hypernetworks_mlps.1.layers.0.bias": "model.safetensors",
21
+ "mask_decoder.output_hypernetworks_mlps.1.layers.0.weight": "model.safetensors",
22
+ "mask_decoder.output_hypernetworks_mlps.1.proj_in.bias": "model.safetensors",
23
+ "mask_decoder.output_hypernetworks_mlps.1.proj_in.weight": "model.safetensors",
24
+ "mask_decoder.output_hypernetworks_mlps.1.proj_out.bias": "model.safetensors",
25
+ "mask_decoder.output_hypernetworks_mlps.1.proj_out.weight": "model.safetensors",
26
+ "mask_decoder.output_hypernetworks_mlps.2.layers.0.bias": "model.safetensors",
27
+ "mask_decoder.output_hypernetworks_mlps.2.layers.0.weight": "model.safetensors",
28
+ "mask_decoder.output_hypernetworks_mlps.2.proj_in.bias": "model.safetensors",
29
+ "mask_decoder.output_hypernetworks_mlps.2.proj_in.weight": "model.safetensors",
30
+ "mask_decoder.output_hypernetworks_mlps.2.proj_out.bias": "model.safetensors",
31
+ "mask_decoder.output_hypernetworks_mlps.2.proj_out.weight": "model.safetensors",
32
+ "mask_decoder.output_hypernetworks_mlps.3.layers.0.bias": "model.safetensors",
33
+ "mask_decoder.output_hypernetworks_mlps.3.layers.0.weight": "model.safetensors",
34
+ "mask_decoder.output_hypernetworks_mlps.3.proj_in.bias": "model.safetensors",
35
+ "mask_decoder.output_hypernetworks_mlps.3.proj_in.weight": "model.safetensors",
36
+ "mask_decoder.output_hypernetworks_mlps.3.proj_out.bias": "model.safetensors",
37
+ "mask_decoder.output_hypernetworks_mlps.3.proj_out.weight": "model.safetensors",
38
+ "mask_decoder.transformer.final_attn_token_to_image.k_proj.bias": "model.safetensors",
39
+ "mask_decoder.transformer.final_attn_token_to_image.k_proj.weight": "model.safetensors",
40
+ "mask_decoder.transformer.final_attn_token_to_image.out_proj.bias": "model.safetensors",
41
+ "mask_decoder.transformer.final_attn_token_to_image.out_proj.weight": "model.safetensors",
42
+ "mask_decoder.transformer.final_attn_token_to_image.q_proj.bias": "model.safetensors",
43
+ "mask_decoder.transformer.final_attn_token_to_image.q_proj.weight": "model.safetensors",
44
+ "mask_decoder.transformer.final_attn_token_to_image.v_proj.bias": "model.safetensors",
45
+ "mask_decoder.transformer.final_attn_token_to_image.v_proj.weight": "model.safetensors",
46
+ "mask_decoder.transformer.layer_norm_final_attn.bias": "model.safetensors",
47
+ "mask_decoder.transformer.layer_norm_final_attn.weight": "model.safetensors",
48
+ "mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.bias": "model.safetensors",
49
+ "mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.weight": "model.safetensors",
50
+ "mask_decoder.transformer.layers.0.cross_attn_image_to_token.out_proj.bias": "model.safetensors",
51
+ "mask_decoder.transformer.layers.0.cross_attn_image_to_token.out_proj.weight": "model.safetensors",
52
+ "mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.bias": "model.safetensors",
53
+ "mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.weight": "model.safetensors",
54
+ "mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.bias": "model.safetensors",
55
+ "mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.weight": "model.safetensors",
56
+ "mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.bias": "model.safetensors",
57
+ "mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.weight": "model.safetensors",
58
+ "mask_decoder.transformer.layers.0.cross_attn_token_to_image.out_proj.bias": "model.safetensors",
59
+ "mask_decoder.transformer.layers.0.cross_attn_token_to_image.out_proj.weight": "model.safetensors",
60
+ "mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.bias": "model.safetensors",
61
+ "mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.weight": "model.safetensors",
62
+ "mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.bias": "model.safetensors",
63
+ "mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.weight": "model.safetensors",
64
+ "mask_decoder.transformer.layers.0.layer_norm1.bias": "model.safetensors",
65
+ "mask_decoder.transformer.layers.0.layer_norm1.weight": "model.safetensors",
66
+ "mask_decoder.transformer.layers.0.layer_norm2.bias": "model.safetensors",
67
+ "mask_decoder.transformer.layers.0.layer_norm2.weight": "model.safetensors",
68
+ "mask_decoder.transformer.layers.0.layer_norm3.bias": "model.safetensors",
69
+ "mask_decoder.transformer.layers.0.layer_norm3.weight": "model.safetensors",
70
+ "mask_decoder.transformer.layers.0.layer_norm4.bias": "model.safetensors",
71
+ "mask_decoder.transformer.layers.0.layer_norm4.weight": "model.safetensors",
72
+ "mask_decoder.transformer.layers.0.mlp.lin1.bias": "model.safetensors",
73
+ "mask_decoder.transformer.layers.0.mlp.lin1.weight": "model.safetensors",
74
+ "mask_decoder.transformer.layers.0.mlp.lin2.bias": "model.safetensors",
75
+ "mask_decoder.transformer.layers.0.mlp.lin2.weight": "model.safetensors",
76
+ "mask_decoder.transformer.layers.0.self_attn.k_proj.bias": "model.safetensors",
77
+ "mask_decoder.transformer.layers.0.self_attn.k_proj.weight": "model.safetensors",
78
+ "mask_decoder.transformer.layers.0.self_attn.out_proj.bias": "model.safetensors",
79
+ "mask_decoder.transformer.layers.0.self_attn.out_proj.weight": "model.safetensors",
80
+ "mask_decoder.transformer.layers.0.self_attn.q_proj.bias": "model.safetensors",
81
+ "mask_decoder.transformer.layers.0.self_attn.q_proj.weight": "model.safetensors",
82
+ "mask_decoder.transformer.layers.0.self_attn.v_proj.bias": "model.safetensors",
83
+ "mask_decoder.transformer.layers.0.self_attn.v_proj.weight": "model.safetensors",
84
+ "mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.bias": "model.safetensors",
85
+ "mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.weight": "model.safetensors",
86
+ "mask_decoder.transformer.layers.1.cross_attn_image_to_token.out_proj.bias": "model.safetensors",
87
+ "mask_decoder.transformer.layers.1.cross_attn_image_to_token.out_proj.weight": "model.safetensors",
88
+ "mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.bias": "model.safetensors",
89
+ "mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.weight": "model.safetensors",
90
+ "mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.bias": "model.safetensors",
91
+ "mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.weight": "model.safetensors",
92
+ "mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.bias": "model.safetensors",
93
+ "mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.weight": "model.safetensors",
94
+ "mask_decoder.transformer.layers.1.cross_attn_token_to_image.out_proj.bias": "model.safetensors",
95
+ "mask_decoder.transformer.layers.1.cross_attn_token_to_image.out_proj.weight": "model.safetensors",
96
+ "mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.bias": "model.safetensors",
97
+ "mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.weight": "model.safetensors",
98
+ "mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.bias": "model.safetensors",
99
+ "mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.weight": "model.safetensors",
100
+ "mask_decoder.transformer.layers.1.layer_norm1.bias": "model.safetensors",
101
+ "mask_decoder.transformer.layers.1.layer_norm1.weight": "model.safetensors",
102
+ "mask_decoder.transformer.layers.1.layer_norm2.bias": "model.safetensors",
103
+ "mask_decoder.transformer.layers.1.layer_norm2.weight": "model.safetensors",
104
+ "mask_decoder.transformer.layers.1.layer_norm3.bias": "model.safetensors",
105
+ "mask_decoder.transformer.layers.1.layer_norm3.weight": "model.safetensors",
106
+ "mask_decoder.transformer.layers.1.layer_norm4.bias": "model.safetensors",
107
+ "mask_decoder.transformer.layers.1.layer_norm4.weight": "model.safetensors",
108
+ "mask_decoder.transformer.layers.1.mlp.lin1.bias": "model.safetensors",
109
+ "mask_decoder.transformer.layers.1.mlp.lin1.weight": "model.safetensors",
110
+ "mask_decoder.transformer.layers.1.mlp.lin2.bias": "model.safetensors",
111
+ "mask_decoder.transformer.layers.1.mlp.lin2.weight": "model.safetensors",
112
+ "mask_decoder.transformer.layers.1.self_attn.k_proj.bias": "model.safetensors",
113
+ "mask_decoder.transformer.layers.1.self_attn.k_proj.weight": "model.safetensors",
114
+ "mask_decoder.transformer.layers.1.self_attn.out_proj.bias": "model.safetensors",
115
+ "mask_decoder.transformer.layers.1.self_attn.out_proj.weight": "model.safetensors",
116
+ "mask_decoder.transformer.layers.1.self_attn.q_proj.bias": "model.safetensors",
117
+ "mask_decoder.transformer.layers.1.self_attn.q_proj.weight": "model.safetensors",
118
+ "mask_decoder.transformer.layers.1.self_attn.v_proj.bias": "model.safetensors",
119
+ "mask_decoder.transformer.layers.1.self_attn.v_proj.weight": "model.safetensors",
120
+ "mask_decoder.upscale_conv1.bias": "model.safetensors",
121
+ "mask_decoder.upscale_conv1.weight": "model.safetensors",
122
+ "mask_decoder.upscale_conv2.bias": "model.safetensors",
123
+ "mask_decoder.upscale_conv2.weight": "model.safetensors",
124
+ "mask_decoder.upscale_layer_norm.bias": "model.safetensors",
125
+ "mask_decoder.upscale_layer_norm.weight": "model.safetensors",
126
+ "prompt_encoder.mask_embed.conv1.bias": "model.safetensors",
127
+ "prompt_encoder.mask_embed.conv1.weight": "model.safetensors",
128
+ "prompt_encoder.mask_embed.conv2.bias": "model.safetensors",
129
+ "prompt_encoder.mask_embed.conv2.weight": "model.safetensors",
130
+ "prompt_encoder.mask_embed.conv3.bias": "model.safetensors",
131
+ "prompt_encoder.mask_embed.conv3.weight": "model.safetensors",
132
+ "prompt_encoder.mask_embed.layer_norm1.bias": "model.safetensors",
133
+ "prompt_encoder.mask_embed.layer_norm1.weight": "model.safetensors",
134
+ "prompt_encoder.mask_embed.layer_norm2.bias": "model.safetensors",
135
+ "prompt_encoder.mask_embed.layer_norm2.weight": "model.safetensors",
136
+ "prompt_encoder.no_mask_embed.weight": "model.safetensors",
137
+ "prompt_encoder.not_a_point_embed.weight": "model.safetensors",
138
+ "prompt_encoder.point_embed.0.weight": "model.safetensors",
139
+ "prompt_encoder.point_embed.1.weight": "model.safetensors",
140
+ "prompt_encoder.point_embed.2.weight": "model.safetensors",
141
+ "prompt_encoder.point_embed.3.weight": "model.safetensors",
142
+ "shared_image_embedding.positional_embedding": "model.safetensors",
143
+ "vision_encoder.layers.0.attn.proj.bias": "model.safetensors",
144
+ "vision_encoder.layers.0.attn.proj.weight": "model.safetensors",
145
+ "vision_encoder.layers.0.attn.qkv.bias": "model.safetensors",
146
+ "vision_encoder.layers.0.attn.qkv.weight": "model.safetensors",
147
+ "vision_encoder.layers.0.attn.rel_pos_h": "model.safetensors",
148
+ "vision_encoder.layers.0.attn.rel_pos_w": "model.safetensors",
149
+ "vision_encoder.layers.0.layer_norm1.bias": "model.safetensors",
150
+ "vision_encoder.layers.0.layer_norm1.weight": "model.safetensors",
151
+ "vision_encoder.layers.0.layer_norm2.bias": "model.safetensors",
152
+ "vision_encoder.layers.0.layer_norm2.weight": "model.safetensors",
153
+ "vision_encoder.layers.0.mlp.lin1.bias": "model.safetensors",
154
+ "vision_encoder.layers.0.mlp.lin1.weight": "model.safetensors",
155
+ "vision_encoder.layers.0.mlp.lin2.bias": "model.safetensors",
156
+ "vision_encoder.layers.0.mlp.lin2.weight": "model.safetensors",
157
+ "vision_encoder.layers.1.attn.proj.bias": "model.safetensors",
158
+ "vision_encoder.layers.1.attn.proj.weight": "model.safetensors",
159
+ "vision_encoder.layers.1.attn.qkv.bias": "model.safetensors",
160
+ "vision_encoder.layers.1.attn.qkv.weight": "model.safetensors",
161
+ "vision_encoder.layers.1.attn.rel_pos_h": "model.safetensors",
162
+ "vision_encoder.layers.1.attn.rel_pos_w": "model.safetensors",
163
+ "vision_encoder.layers.1.layer_norm1.bias": "model.safetensors",
164
+ "vision_encoder.layers.1.layer_norm1.weight": "model.safetensors",
165
+ "vision_encoder.layers.1.layer_norm2.bias": "model.safetensors",
166
+ "vision_encoder.layers.1.layer_norm2.weight": "model.safetensors",
167
+ "vision_encoder.layers.1.mlp.lin1.bias": "model.safetensors",
168
+ "vision_encoder.layers.1.mlp.lin1.weight": "model.safetensors",
169
+ "vision_encoder.layers.1.mlp.lin2.bias": "model.safetensors",
170
+ "vision_encoder.layers.1.mlp.lin2.weight": "model.safetensors",
171
+ "vision_encoder.layers.10.attn.proj.bias": "model.safetensors",
172
+ "vision_encoder.layers.10.attn.proj.weight": "model.safetensors",
173
+ "vision_encoder.layers.10.attn.qkv.bias": "model.safetensors",
174
+ "vision_encoder.layers.10.attn.qkv.weight": "model.safetensors",
175
+ "vision_encoder.layers.10.attn.rel_pos_h": "model.safetensors",
176
+ "vision_encoder.layers.10.attn.rel_pos_w": "model.safetensors",
177
+ "vision_encoder.layers.10.layer_norm1.bias": "model.safetensors",
178
+ "vision_encoder.layers.10.layer_norm1.weight": "model.safetensors",
179
+ "vision_encoder.layers.10.layer_norm2.bias": "model.safetensors",
180
+ "vision_encoder.layers.10.layer_norm2.weight": "model.safetensors",
181
+ "vision_encoder.layers.10.mlp.lin1.bias": "model.safetensors",
182
+ "vision_encoder.layers.10.mlp.lin1.weight": "model.safetensors",
183
+ "vision_encoder.layers.10.mlp.lin2.bias": "model.safetensors",
184
+ "vision_encoder.layers.10.mlp.lin2.weight": "model.safetensors",
185
+ "vision_encoder.layers.11.attn.proj.bias": "model.safetensors",
186
+ "vision_encoder.layers.11.attn.proj.weight": "model.safetensors",
187
+ "vision_encoder.layers.11.attn.qkv.bias": "model.safetensors",
188
+ "vision_encoder.layers.11.attn.qkv.weight": "model.safetensors",
189
+ "vision_encoder.layers.11.attn.rel_pos_h": "model.safetensors",
190
+ "vision_encoder.layers.11.attn.rel_pos_w": "model.safetensors",
191
+ "vision_encoder.layers.11.layer_norm1.bias": "model.safetensors",
192
+ "vision_encoder.layers.11.layer_norm1.weight": "model.safetensors",
193
+ "vision_encoder.layers.11.layer_norm2.bias": "model.safetensors",
194
+ "vision_encoder.layers.11.layer_norm2.weight": "model.safetensors",
195
+ "vision_encoder.layers.11.mlp.lin1.bias": "model.safetensors",
196
+ "vision_encoder.layers.11.mlp.lin1.weight": "model.safetensors",
197
+ "vision_encoder.layers.11.mlp.lin2.bias": "model.safetensors",
198
+ "vision_encoder.layers.11.mlp.lin2.weight": "model.safetensors",
199
+ "vision_encoder.layers.2.attn.proj.bias": "model.safetensors",
200
+ "vision_encoder.layers.2.attn.proj.weight": "model.safetensors",
201
+ "vision_encoder.layers.2.attn.qkv.bias": "model.safetensors",
202
+ "vision_encoder.layers.2.attn.qkv.weight": "model.safetensors",
203
+ "vision_encoder.layers.2.attn.rel_pos_h": "model.safetensors",
204
+ "vision_encoder.layers.2.attn.rel_pos_w": "model.safetensors",
205
+ "vision_encoder.layers.2.layer_norm1.bias": "model.safetensors",
206
+ "vision_encoder.layers.2.layer_norm1.weight": "model.safetensors",
207
+ "vision_encoder.layers.2.layer_norm2.bias": "model.safetensors",
208
+ "vision_encoder.layers.2.layer_norm2.weight": "model.safetensors",
209
+ "vision_encoder.layers.2.mlp.lin1.bias": "model.safetensors",
210
+ "vision_encoder.layers.2.mlp.lin1.weight": "model.safetensors",
211
+ "vision_encoder.layers.2.mlp.lin2.bias": "model.safetensors",
212
+ "vision_encoder.layers.2.mlp.lin2.weight": "model.safetensors",
213
+ "vision_encoder.layers.3.attn.proj.bias": "model.safetensors",
214
+ "vision_encoder.layers.3.attn.proj.weight": "model.safetensors",
215
+ "vision_encoder.layers.3.attn.qkv.bias": "model.safetensors",
216
+ "vision_encoder.layers.3.attn.qkv.weight": "model.safetensors",
217
+ "vision_encoder.layers.3.attn.rel_pos_h": "model.safetensors",
218
+ "vision_encoder.layers.3.attn.rel_pos_w": "model.safetensors",
219
+ "vision_encoder.layers.3.layer_norm1.bias": "model.safetensors",
220
+ "vision_encoder.layers.3.layer_norm1.weight": "model.safetensors",
221
+ "vision_encoder.layers.3.layer_norm2.bias": "model.safetensors",
222
+ "vision_encoder.layers.3.layer_norm2.weight": "model.safetensors",
223
+ "vision_encoder.layers.3.mlp.lin1.bias": "model.safetensors",
224
+ "vision_encoder.layers.3.mlp.lin1.weight": "model.safetensors",
225
+ "vision_encoder.layers.3.mlp.lin2.bias": "model.safetensors",
226
+ "vision_encoder.layers.3.mlp.lin2.weight": "model.safetensors",
227
+ "vision_encoder.layers.4.attn.proj.bias": "model.safetensors",
228
+ "vision_encoder.layers.4.attn.proj.weight": "model.safetensors",
229
+ "vision_encoder.layers.4.attn.qkv.bias": "model.safetensors",
230
+ "vision_encoder.layers.4.attn.qkv.weight": "model.safetensors",
231
+ "vision_encoder.layers.4.attn.rel_pos_h": "model.safetensors",
232
+ "vision_encoder.layers.4.attn.rel_pos_w": "model.safetensors",
233
+ "vision_encoder.layers.4.layer_norm1.bias": "model.safetensors",
234
+ "vision_encoder.layers.4.layer_norm1.weight": "model.safetensors",
235
+ "vision_encoder.layers.4.layer_norm2.bias": "model.safetensors",
236
+ "vision_encoder.layers.4.layer_norm2.weight": "model.safetensors",
237
+ "vision_encoder.layers.4.mlp.lin1.bias": "model.safetensors",
238
+ "vision_encoder.layers.4.mlp.lin1.weight": "model.safetensors",
239
+ "vision_encoder.layers.4.mlp.lin2.bias": "model.safetensors",
240
+ "vision_encoder.layers.4.mlp.lin2.weight": "model.safetensors",
241
+ "vision_encoder.layers.5.attn.proj.bias": "model.safetensors",
242
+ "vision_encoder.layers.5.attn.proj.weight": "model.safetensors",
243
+ "vision_encoder.layers.5.attn.qkv.bias": "model.safetensors",
244
+ "vision_encoder.layers.5.attn.qkv.weight": "model.safetensors",
245
+ "vision_encoder.layers.5.attn.rel_pos_h": "model.safetensors",
246
+ "vision_encoder.layers.5.attn.rel_pos_w": "model.safetensors",
247
+ "vision_encoder.layers.5.layer_norm1.bias": "model.safetensors",
248
+ "vision_encoder.layers.5.layer_norm1.weight": "model.safetensors",
249
+ "vision_encoder.layers.5.layer_norm2.bias": "model.safetensors",
250
+ "vision_encoder.layers.5.layer_norm2.weight": "model.safetensors",
251
+ "vision_encoder.layers.5.mlp.lin1.bias": "model.safetensors",
252
+ "vision_encoder.layers.5.mlp.lin1.weight": "model.safetensors",
253
+ "vision_encoder.layers.5.mlp.lin2.bias": "model.safetensors",
254
+ "vision_encoder.layers.5.mlp.lin2.weight": "model.safetensors",
255
+ "vision_encoder.layers.6.attn.proj.bias": "model.safetensors",
256
+ "vision_encoder.layers.6.attn.proj.weight": "model.safetensors",
257
+ "vision_encoder.layers.6.attn.qkv.bias": "model.safetensors",
258
+ "vision_encoder.layers.6.attn.qkv.weight": "model.safetensors",
259
+ "vision_encoder.layers.6.attn.rel_pos_h": "model.safetensors",
260
+ "vision_encoder.layers.6.attn.rel_pos_w": "model.safetensors",
261
+ "vision_encoder.layers.6.layer_norm1.bias": "model.safetensors",
262
+ "vision_encoder.layers.6.layer_norm1.weight": "model.safetensors",
263
+ "vision_encoder.layers.6.layer_norm2.bias": "model.safetensors",
264
+ "vision_encoder.layers.6.layer_norm2.weight": "model.safetensors",
265
+ "vision_encoder.layers.6.mlp.lin1.bias": "model.safetensors",
266
+ "vision_encoder.layers.6.mlp.lin1.weight": "model.safetensors",
267
+ "vision_encoder.layers.6.mlp.lin2.bias": "model.safetensors",
268
+ "vision_encoder.layers.6.mlp.lin2.weight": "model.safetensors",
269
+ "vision_encoder.layers.7.attn.proj.bias": "model.safetensors",
270
+ "vision_encoder.layers.7.attn.proj.weight": "model.safetensors",
271
+ "vision_encoder.layers.7.attn.qkv.bias": "model.safetensors",
272
+ "vision_encoder.layers.7.attn.qkv.weight": "model.safetensors",
273
+ "vision_encoder.layers.7.attn.rel_pos_h": "model.safetensors",
274
+ "vision_encoder.layers.7.attn.rel_pos_w": "model.safetensors",
275
+ "vision_encoder.layers.7.layer_norm1.bias": "model.safetensors",
276
+ "vision_encoder.layers.7.layer_norm1.weight": "model.safetensors",
277
+ "vision_encoder.layers.7.layer_norm2.bias": "model.safetensors",
278
+ "vision_encoder.layers.7.layer_norm2.weight": "model.safetensors",
279
+ "vision_encoder.layers.7.mlp.lin1.bias": "model.safetensors",
280
+ "vision_encoder.layers.7.mlp.lin1.weight": "model.safetensors",
281
+ "vision_encoder.layers.7.mlp.lin2.bias": "model.safetensors",
282
+ "vision_encoder.layers.7.mlp.lin2.weight": "model.safetensors",
283
+ "vision_encoder.layers.8.attn.proj.bias": "model.safetensors",
284
+ "vision_encoder.layers.8.attn.proj.weight": "model.safetensors",
285
+ "vision_encoder.layers.8.attn.qkv.bias": "model.safetensors",
286
+ "vision_encoder.layers.8.attn.qkv.weight": "model.safetensors",
287
+ "vision_encoder.layers.8.attn.rel_pos_h": "model.safetensors",
288
+ "vision_encoder.layers.8.attn.rel_pos_w": "model.safetensors",
289
+ "vision_encoder.layers.8.layer_norm1.bias": "model.safetensors",
290
+ "vision_encoder.layers.8.layer_norm1.weight": "model.safetensors",
291
+ "vision_encoder.layers.8.layer_norm2.bias": "model.safetensors",
292
+ "vision_encoder.layers.8.layer_norm2.weight": "model.safetensors",
293
+ "vision_encoder.layers.8.mlp.lin1.bias": "model.safetensors",
294
+ "vision_encoder.layers.8.mlp.lin1.weight": "model.safetensors",
295
+ "vision_encoder.layers.8.mlp.lin2.bias": "model.safetensors",
296
+ "vision_encoder.layers.8.mlp.lin2.weight": "model.safetensors",
297
+ "vision_encoder.layers.9.attn.proj.bias": "model.safetensors",
298
+ "vision_encoder.layers.9.attn.proj.weight": "model.safetensors",
299
+ "vision_encoder.layers.9.attn.qkv.bias": "model.safetensors",
300
+ "vision_encoder.layers.9.attn.qkv.weight": "model.safetensors",
301
+ "vision_encoder.layers.9.attn.rel_pos_h": "model.safetensors",
302
+ "vision_encoder.layers.9.attn.rel_pos_w": "model.safetensors",
303
+ "vision_encoder.layers.9.layer_norm1.bias": "model.safetensors",
304
+ "vision_encoder.layers.9.layer_norm1.weight": "model.safetensors",
305
+ "vision_encoder.layers.9.layer_norm2.bias": "model.safetensors",
306
+ "vision_encoder.layers.9.layer_norm2.weight": "model.safetensors",
307
+ "vision_encoder.layers.9.mlp.lin1.bias": "model.safetensors",
308
+ "vision_encoder.layers.9.mlp.lin1.weight": "model.safetensors",
309
+ "vision_encoder.layers.9.mlp.lin2.bias": "model.safetensors",
310
+ "vision_encoder.layers.9.mlp.lin2.weight": "model.safetensors",
311
+ "vision_encoder.neck.conv1.weight": "model.safetensors",
312
+ "vision_encoder.neck.conv2.weight": "model.safetensors",
313
+ "vision_encoder.neck.layer_norm1.bias": "model.safetensors",
314
+ "vision_encoder.neck.layer_norm1.weight": "model.safetensors",
315
+ "vision_encoder.neck.layer_norm2.bias": "model.safetensors",
316
+ "vision_encoder.neck.layer_norm2.weight": "model.safetensors",
317
+ "vision_encoder.patch_embed.projection.bias": "model.safetensors",
318
+ "vision_encoder.patch_embed.projection.weight": "model.safetensors",
319
+ "vision_encoder.pos_embed": "model.safetensors"
320
+ }
321
+ }