Hugging Face's logo

ArthurZ
/
sam-vit-huge

Transformers
PyTorch
sam
Inference Endpoints
Model card Files Community
ArthurZ HF staff commited on
Commit
aeecbf8
•
1 Parent(s): 5d1da0c

Upload SamForMaskGeneration

Browse files
Files changed (2) hide show
  1. config.json +252 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,252 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "6348709526ae7b665d67f5dadec06e10f09c6804",
3
+ "_name_or_path": "ybelkada/sam-vit-h",
4
+ "architectures": [
5
+ "SamForMaskGeneration"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "initializer_range": 0.02,
9
+ "mask_decoder_config": {
10
+ "_name_or_path": "",
11
+ "add_cross_attention": false,
12
+ "architectures": null,
13
+ "attention_downsample_rate": 2,
14
+ "bad_words_ids": null,
15
+ "begin_suppress_tokens": null,
16
+ "bos_token_id": null,
17
+ "chunk_size_feed_forward": 0,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": null,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "hidden_act": "relu",
30
+ "hidden_size": 256,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "iou_head_depth": 3,
36
+ "iou_head_hidden_dim": 256,
37
+ "is_decoder": false,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1
42
+ },
43
+ "layer_norm_eps": 1e-06,
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "min_length": 0,
47
+ "mlp_dim": 2048,
48
+ "model_type": "",
49
+ "no_repeat_ngram_size": 0,
50
+ "num_attention_heads": 8,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_hidden_layers": 2,
54
+ "num_multimask_outputs": 3,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": null,
60
+ "prefix": null,
61
+ "problem_type": null,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "repetition_penalty": 1.0,
65
+ "return_dict": true,
66
+ "return_dict_in_generate": false,
67
+ "sep_token_id": null,
68
+ "suppress_tokens": null,
69
+ "task_specific_params": null,
70
+ "temperature": 1.0,
71
+ "tf_legacy_loss": false,
72
+ "tie_encoder_decoder": false,
73
+ "tie_word_embeddings": true,
74
+ "tokenizer_class": null,
75
+ "top_k": 50,
76
+ "top_p": 1.0,
77
+ "torch_dtype": null,
78
+ "torchscript": false,
79
+ "transformers_version": "4.29.0.dev0",
80
+ "typical_p": 1.0,
81
+ "use_bfloat16": false
82
+ },
83
+ "model_type": "sam",
84
+ "prompt_encoder_config": {
85
+ "_name_or_path": "",
86
+ "add_cross_attention": false,
87
+ "architectures": null,
88
+ "bad_words_ids": null,
89
+ "begin_suppress_tokens": null,
90
+ "bos_token_id": null,
91
+ "chunk_size_feed_forward": 0,
92
+ "cross_attention_hidden_size": null,
93
+ "decoder_start_token_id": null,
94
+ "diversity_penalty": 0.0,
95
+ "do_sample": false,
96
+ "early_stopping": false,
97
+ "encoder_no_repeat_ngram_size": 0,
98
+ "eos_token_id": null,
99
+ "exponential_decay_length_penalty": null,
100
+ "finetuning_task": null,
101
+ "forced_bos_token_id": null,
102
+ "forced_eos_token_id": null,
103
+ "hidden_act": "gelu",
104
+ "hidden_size": 256,
105
+ "id2label": {
106
+ "0": "LABEL_0",
107
+ "1": "LABEL_1"
108
+ },
109
+ "image_embedding_size": 64,
110
+ "image_size": 1024,
111
+ "input_image_size": 1024,
112
+ "is_decoder": false,
113
+ "is_encoder_decoder": false,
114
+ "label2id": {
115
+ "LABEL_0": 0,
116
+ "LABEL_1": 1
117
+ },
118
+ "layer_norm_eps": 1e-06,
119
+ "length_penalty": 1.0,
120
+ "mask_input_channels": 16,
121
+ "max_length": 20,
122
+ "min_length": 0,
123
+ "model_type": "",
124
+ "no_repeat_ngram_size": 0,
125
+ "num_beam_groups": 1,
126
+ "num_beams": 1,
127
+ "num_point_embeddings": 4,
128
+ "num_return_sequences": 1,
129
+ "output_attentions": false,
130
+ "output_hidden_states": false,
131
+ "output_scores": false,
132
+ "pad_token_id": null,
133
+ "patch_size": 16,
134
+ "prefix": null,
135
+ "problem_type": null,
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
+ "suppress_tokens": null,
143
+ "task_specific_params": null,
144
+ "temperature": 1.0,
145
+ "tf_legacy_loss": false,
146
+ "tie_encoder_decoder": false,
147
+ "tie_word_embeddings": true,
148
+ "tokenizer_class": null,
149
+ "top_k": 50,
150
+ "top_p": 1.0,
151
+ "torch_dtype": null,
152
+ "torchscript": false,
153
+ "transformers_version": "4.29.0.dev0",
154
+ "typical_p": 1.0,
155
+ "use_bfloat16": false
156
+ },
157
+ "torch_dtype": "float32",
158
+ "transformers_version": null,
159
+ "vision_config": {
160
+ "_name_or_path": "",
161
+ "add_cross_attention": false,
162
+ "architectures": null,
163
+ "attention_dropout": 0.0,
164
+ "bad_words_ids": null,
165
+ "begin_suppress_tokens": null,
166
+ "bos_token_id": null,
167
+ "chunk_size_feed_forward": 0,
168
+ "cross_attention_hidden_size": null,
169
+ "decoder_start_token_id": null,
170
+ "diversity_penalty": 0.0,
171
+ "do_sample": false,
172
+ "dropout": 0.0,
173
+ "early_stopping": false,
174
+ "encoder_no_repeat_ngram_size": 0,
175
+ "eos_token_id": null,
176
+ "exponential_decay_length_penalty": null,
177
+ "finetuning_task": null,
178
+ "forced_bos_token_id": null,
179
+ "forced_eos_token_id": null,
180
+ "global_attn_indexes": [
181
+ 7,
182
+ 15,
183
+ 23,
184
+ 31
185
+ ],
186
+ "hidden_act": "gelu",
187
+ "hidden_size": 1280,
188
+ "id2label": {
189
+ "0": "LABEL_0",
190
+ "1": "LABEL_1"
191
+ },
192
+ "image_size": 1024,
193
+ "initializer_factor": 1.0,
194
+ "initializer_range": 1e-10,
195
+ "intermediate_size": 6144,
196
+ "is_decoder": false,
197
+ "is_encoder_decoder": false,
198
+ "label2id": {
199
+ "LABEL_0": 0,
200
+ "LABEL_1": 1
201
+ },
202
+ "layer_norm_eps": 1e-06,
203
+ "length_penalty": 1.0,
204
+ "max_length": 20,
205
+ "min_length": 0,
206
+ "mlp_dim": 5120,
207
+ "mlp_ratio": 4.0,
208
+ "model_type": "",
209
+ "no_repeat_ngram_size": 0,
210
+ "num_attention_heads": 16,
211
+ "num_beam_groups": 1,
212
+ "num_beams": 1,
213
+ "num_channels": 3,
214
+ "num_hidden_layers": 32,
215
+ "num_pos_feats": 128,
216
+ "num_return_sequences": 1,
217
+ "output_attentions": false,
218
+ "output_channels": 256,
219
+ "output_hidden_states": false,
220
+ "output_scores": false,
221
+ "pad_token_id": null,
222
+ "patch_size": 16,
223
+ "prefix": null,
224
+ "problem_type": null,
225
+ "projection_dim": 512,
226
+ "pruned_heads": {},
227
+ "qkv_bias": true,
228
+ "rel_pos_zero_init": false,
229
+ "remove_invalid_values": false,
230
+ "repetition_penalty": 1.0,
231
+ "return_dict": true,
232
+ "return_dict_in_generate": false,
233
+ "sep_token_id": null,
234
+ "suppress_tokens": null,
235
+ "task_specific_params": null,
236
+ "temperature": 1.0,
237
+ "tf_legacy_loss": false,
238
+ "tie_encoder_decoder": false,
239
+ "tie_word_embeddings": true,
240
+ "tokenizer_class": null,
241
+ "top_k": 50,
242
+ "top_p": 1.0,
243
+ "torch_dtype": null,
244
+ "torchscript": false,
245
+ "transformers_version": "4.29.0.dev0",
246
+ "typical_p": 1.0,
247
+ "use_abs_pos": true,
248
+ "use_bfloat16": false,
249
+ "use_rel_pos": true,
250
+ "window_size": 14
251
+ }
252
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:935070f0d067463285f68cbf5e2453966ae5cf87f0724e074b68c19241b34632
3
+ size 2564556693