Hugging Face's logo

facebook
/
sam-vit-large

Mask Generation
Transformers
PyTorch
TensorFlow
Safetensors
sam
vision
Inference Endpoints
Model card Files Community
5
ybelkada HF staff commited on
Commit
341c9ba
•
1 Parent(s): 74c53d5

Upload model

Browse files
Files changed (2) hide show
  1. config.json +248 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "SamModel"
5
+ ],
6
+ "initializer_range": 0.02,
7
+ "mask_decoder_config": {
8
+ "_name_or_path": "",
9
+ "add_cross_attention": false,
10
+ "architectures": null,
11
+ "attention_downsample_rate": 2,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "hidden_act": "relu",
28
+ "hidden_size": 256,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "iou_head_depth": 3,
34
+ "iou_head_hidden_dim": 256,
35
+ "is_decoder": false,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_eps": 1e-06,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "min_length": 0,
45
+ "mlp_dim": 2048,
46
+ "model_type": "",
47
+ "no_repeat_ngram_size": 0,
48
+ "num_attention_heads": 8,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_hidden_layers": 2,
52
+ "num_multimask_outputs": 3,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": null,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "sep_token_id": null,
66
+ "suppress_tokens": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tf_legacy_loss": false,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "transformers_version": "4.29.0.dev0",
78
+ "typical_p": 1.0,
79
+ "use_bfloat16": false
80
+ },
81
+ "model_type": "sam",
82
+ "prompt_encoder_config": {
83
+ "_name_or_path": "",
84
+ "add_cross_attention": false,
85
+ "architectures": null,
86
+ "bad_words_ids": null,
87
+ "begin_suppress_tokens": null,
88
+ "bos_token_id": null,
89
+ "chunk_size_feed_forward": 0,
90
+ "cross_attention_hidden_size": null,
91
+ "decoder_start_token_id": null,
92
+ "diversity_penalty": 0.0,
93
+ "do_sample": false,
94
+ "early_stopping": false,
95
+ "encoder_no_repeat_ngram_size": 0,
96
+ "eos_token_id": null,
97
+ "exponential_decay_length_penalty": null,
98
+ "finetuning_task": null,
99
+ "forced_bos_token_id": null,
100
+ "forced_eos_token_id": null,
101
+ "hidden_act": "gelu",
102
+ "hidden_size": 256,
103
+ "id2label": {
104
+ "0": "LABEL_0",
105
+ "1": "LABEL_1"
106
+ },
107
+ "image_embedding_size": 64,
108
+ "image_size": 1024,
109
+ "is_decoder": false,
110
+ "is_encoder_decoder": false,
111
+ "label2id": {
112
+ "LABEL_0": 0,
113
+ "LABEL_1": 1
114
+ },
115
+ "layer_norm_eps": 1e-06,
116
+ "length_penalty": 1.0,
117
+ "mask_input_channels": 16,
118
+ "max_length": 20,
119
+ "min_length": 0,
120
+ "model_type": "",
121
+ "no_repeat_ngram_size": 0,
122
+ "num_beam_groups": 1,
123
+ "num_beams": 1,
124
+ "num_point_embeddings": 4,
125
+ "num_return_sequences": 1,
126
+ "output_attentions": false,
127
+ "output_hidden_states": false,
128
+ "output_scores": false,
129
+ "pad_token_id": null,
130
+ "patch_size": 16,
131
+ "prefix": null,
132
+ "problem_type": null,
133
+ "pruned_heads": {},
134
+ "remove_invalid_values": false,
135
+ "repetition_penalty": 1.0,
136
+ "return_dict": true,
137
+ "return_dict_in_generate": false,
138
+ "sep_token_id": null,
139
+ "suppress_tokens": null,
140
+ "task_specific_params": null,
141
+ "temperature": 1.0,
142
+ "tf_legacy_loss": false,
143
+ "tie_encoder_decoder": false,
144
+ "tie_word_embeddings": true,
145
+ "tokenizer_class": null,
146
+ "top_k": 50,
147
+ "top_p": 1.0,
148
+ "torch_dtype": null,
149
+ "torchscript": false,
150
+ "transformers_version": "4.29.0.dev0",
151
+ "typical_p": 1.0,
152
+ "use_bfloat16": false
153
+ },
154
+ "torch_dtype": "float32",
155
+ "transformers_version": null,
156
+ "vision_config": {
157
+ "_name_or_path": "",
158
+ "add_cross_attention": false,
159
+ "architectures": null,
160
+ "attention_dropout": 0.0,
161
+ "bad_words_ids": null,
162
+ "begin_suppress_tokens": null,
163
+ "bos_token_id": null,
164
+ "chunk_size_feed_forward": 0,
165
+ "cross_attention_hidden_size": null,
166
+ "decoder_start_token_id": null,
167
+ "diversity_penalty": 0.0,
168
+ "do_sample": false,
169
+ "dropout": 0.0,
170
+ "early_stopping": false,
171
+ "encoder_no_repeat_ngram_size": 0,
172
+ "eos_token_id": null,
173
+ "exponential_decay_length_penalty": null,
174
+ "finetuning_task": null,
175
+ "forced_bos_token_id": null,
176
+ "forced_eos_token_id": null,
177
+ "global_attn_indexes": [
178
+ 5,
179
+ 11,
180
+ 17,
181
+ 23
182
+ ],
183
+ "hidden_act": "gelu",
184
+ "hidden_size": 1024,
185
+ "id2label": {
186
+ "0": "LABEL_0",
187
+ "1": "LABEL_1"
188
+ },
189
+ "image_size": 1024,
190
+ "initializer_factor": 1.0,
191
+ "initializer_range": 1e-10,
192
+ "intermediate_size": 6144,
193
+ "is_decoder": false,
194
+ "is_encoder_decoder": false,
195
+ "label2id": {
196
+ "LABEL_0": 0,
197
+ "LABEL_1": 1
198
+ },
199
+ "layer_norm_eps": 1e-06,
200
+ "length_penalty": 1.0,
201
+ "max_length": 20,
202
+ "min_length": 0,
203
+ "mlp_dim": 4096,
204
+ "mlp_ratio": 4.0,
205
+ "model_type": "",
206
+ "no_repeat_ngram_size": 0,
207
+ "num_attention_heads": 16,
208
+ "num_beam_groups": 1,
209
+ "num_beams": 1,
210
+ "num_channels": 3,
211
+ "num_hidden_layers": 24,
212
+ "num_pos_feats": 128,
213
+ "num_return_sequences": 1,
214
+ "output_attentions": false,
215
+ "output_channels": 256,
216
+ "output_hidden_states": false,
217
+ "output_scores": false,
218
+ "pad_token_id": null,
219
+ "patch_size": 16,
220
+ "prefix": null,
221
+ "problem_type": null,
222
+ "projection_dim": 512,
223
+ "pruned_heads": {},
224
+ "qkv_bias": true,
225
+ "remove_invalid_values": false,
226
+ "repetition_penalty": 1.0,
227
+ "return_dict": true,
228
+ "return_dict_in_generate": false,
229
+ "sep_token_id": null,
230
+ "suppress_tokens": null,
231
+ "task_specific_params": null,
232
+ "temperature": 1.0,
233
+ "tf_legacy_loss": false,
234
+ "tie_encoder_decoder": false,
235
+ "tie_word_embeddings": true,
236
+ "tokenizer_class": null,
237
+ "top_k": 50,
238
+ "top_p": 1.0,
239
+ "torch_dtype": null,
240
+ "torchscript": false,
241
+ "transformers_version": "4.29.0.dev0",
242
+ "typical_p": 1.0,
243
+ "use_abs_pos": true,
244
+ "use_bfloat16": false,
245
+ "use_rel_pos": true,
246
+ "window_size": 14
247
+ }
248
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:149bba0bfe0b10f856adb815c37000978ceda04ed3a373c54e565645ae6b7c53
3
+ size 1249536149