Hugging Face's logo

jadechoghari
/
robustsam-vit-base

Mask Generation
Transformers
Safetensors
sam
Inference Endpoints
Model card Files Community
jadechoghari commited on
Commit
98b1e5d
•
1 Parent(s): 33cbbf4

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +236 -5
config.json CHANGED
@@ -1,18 +1,249 @@
1
  {
 
 
2
  "architectures": [
3
  "SamModel"
4
  ],
5
  "initializer_range": 0.02,
6
  "mask_decoder_config": {
7
- "model_type": ""
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  },
9
  "model_type": "sam",
10
  "prompt_encoder_config": {
11
- "model_type": ""
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  },
13
  "torch_dtype": "float32",
14
- "transformers_version": "4.42.4",
15
  "vision_config": {
16
- "model_type": ""
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  }
18
- }
 
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
+ }