weic22 commited on
Commit
a748a5b
1 Parent(s): 434976c

HyperSeg-3B version 1

Browse files
added_tokens.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257,
40
+ "[SEG]": 50295
41
+ }
config.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/Mipha-3B",
3
+ "architectures": [
4
+ "HyperSeg"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "embd_pdrop": 0.0,
9
+ "eos_token_id": 2,
10
+ "freeze_vision_tower": false,
11
+ "hidden_act": "gelu_new",
12
+ "hidden_size": 2560,
13
+ "image_aspect_ratio": "pad",
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 10240,
16
+ "layer_norm_eps": 1e-05,
17
+ "mask_decode_train": true,
18
+ "max_position_embeddings": 2048,
19
+ "mm_projector_lr": null,
20
+ "mm_use_im_patch_token": false,
21
+ "mm_use_im_start_end": false,
22
+ "mm_vision_tower": "/siglip-so400m-patch14-384",
23
+ "model_type": "mipha_phi",
24
+ "non_lora_lr": null,
25
+ "num_attention_heads": 32,
26
+ "num_hidden_layers": 32,
27
+ "num_key_value_heads": 32,
28
+ "partial_rotary_factor": 0.4,
29
+ "pretraining_tp": 1,
30
+ "qk_layernorm": false,
31
+ "resid_pdrop": 0.1,
32
+ "rope_scaling": null,
33
+ "rope_theta": 10000.0,
34
+ "swin_type": "base",
35
+ "tie_word_embeddings": false,
36
+ "tokenizer_model_max_length": 2048,
37
+ "tokenizer_padding_side": "right",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.38.2",
40
+ "tune_mm_mlp_adapter": true,
41
+ "use_cache": true,
42
+ "use_mm_proj": true,
43
+ "vision_config": {
44
+ "mm_projector": {
45
+ "_name_or_path": "",
46
+ "add_cross_attention": false,
47
+ "architectures": null,
48
+ "bad_words_ids": null,
49
+ "begin_suppress_tokens": null,
50
+ "bos_token_id": null,
51
+ "chunk_size_feed_forward": 0,
52
+ "cross_attention_hidden_size": null,
53
+ "decoder_start_token_id": null,
54
+ "diversity_penalty": 0.0,
55
+ "do_sample": false,
56
+ "early_stopping": false,
57
+ "encoder_no_repeat_ngram_size": 0,
58
+ "eos_token_id": null,
59
+ "exponential_decay_length_penalty": null,
60
+ "finetuning_task": null,
61
+ "forced_bos_token_id": null,
62
+ "forced_eos_token_id": null,
63
+ "hidden_size": 2560,
64
+ "id2label": {
65
+ "0": "LABEL_0",
66
+ "1": "LABEL_1"
67
+ },
68
+ "is_decoder": false,
69
+ "is_encoder_decoder": false,
70
+ "label2id": {
71
+ "LABEL_0": 0,
72
+ "LABEL_1": 1
73
+ },
74
+ "length_penalty": 1.0,
75
+ "max_length": 20,
76
+ "min_length": 0,
77
+ "mm_hidden_size": 1152,
78
+ "mm_projector_type": "mlp2x_gelu",
79
+ "model_type": "mipha_projector",
80
+ "no_repeat_ngram_size": 0,
81
+ "num_beam_groups": 1,
82
+ "num_beams": 1,
83
+ "num_return_sequences": 1,
84
+ "output_attentions": false,
85
+ "output_hidden_states": false,
86
+ "output_scores": false,
87
+ "pad_token_id": null,
88
+ "prefix": null,
89
+ "problem_type": null,
90
+ "pruned_heads": {},
91
+ "remove_invalid_values": false,
92
+ "repetition_penalty": 1.0,
93
+ "return_dict": true,
94
+ "return_dict_in_generate": false,
95
+ "sep_token_id": null,
96
+ "suppress_tokens": null,
97
+ "task_specific_params": null,
98
+ "temperature": 1.0,
99
+ "tf_legacy_loss": false,
100
+ "tie_encoder_decoder": false,
101
+ "tie_word_embeddings": true,
102
+ "tokenizer_class": null,
103
+ "top_k": 50,
104
+ "top_p": 1.0,
105
+ "torch_dtype": null,
106
+ "torchscript": false,
107
+ "transformers_version": "4.37.1",
108
+ "typical_p": 1.0,
109
+ "use_bfloat16": false
110
+ },
111
+ "vision_tower": {
112
+ "_name_or_path": "",
113
+ "add_cross_attention": false,
114
+ "architectures": null,
115
+ "attention_dropout": 0.0,
116
+ "bad_words_ids": null,
117
+ "begin_suppress_tokens": null,
118
+ "bos_token_id": null,
119
+ "chunk_size_feed_forward": 0,
120
+ "cross_attention_hidden_size": null,
121
+ "decoder_start_token_id": null,
122
+ "diversity_penalty": 0.0,
123
+ "do_sample": false,
124
+ "early_stopping": false,
125
+ "encoder_no_repeat_ngram_size": 0,
126
+ "eos_token_id": null,
127
+ "exponential_decay_length_penalty": null,
128
+ "finetuning_task": null,
129
+ "forced_bos_token_id": null,
130
+ "forced_eos_token_id": null,
131
+ "hidden_act": "gelu_pytorch_tanh",
132
+ "hidden_size": 1152,
133
+ "id2label": {
134
+ "0": "LABEL_0",
135
+ "1": "LABEL_1"
136
+ },
137
+ "image_size": 384,
138
+ "initializer_factor": 1.0,
139
+ "initializer_range": 0.02,
140
+ "intermediate_size": 4304,
141
+ "is_decoder": false,
142
+ "is_encoder_decoder": false,
143
+ "label2id": {
144
+ "LABEL_0": 0,
145
+ "LABEL_1": 1
146
+ },
147
+ "layer_norm_eps": 1e-06,
148
+ "length_penalty": 1.0,
149
+ "max_length": 20,
150
+ "min_length": 0,
151
+ "mm_vision_select_feature": "patch",
152
+ "mm_vision_select_layer": -2,
153
+ "model_type": "mipha_vision_model",
154
+ "no_repeat_ngram_size": 0,
155
+ "num_attention_heads": 16,
156
+ "num_beam_groups": 1,
157
+ "num_beams": 1,
158
+ "num_channels": 3,
159
+ "num_hidden_layers": 27,
160
+ "num_return_sequences": 1,
161
+ "output_attentions": false,
162
+ "output_hidden_states": false,
163
+ "output_scores": false,
164
+ "pad_token_id": null,
165
+ "patch_size": 14,
166
+ "prefix": null,
167
+ "problem_type": null,
168
+ "projection_dim": 512,
169
+ "pruned_heads": {},
170
+ "remove_invalid_values": false,
171
+ "repetition_penalty": 1.0,
172
+ "return_dict": true,
173
+ "return_dict_in_generate": false,
174
+ "sep_token_id": null,
175
+ "suppress_tokens": null,
176
+ "task_specific_params": null,
177
+ "temperature": 1.0,
178
+ "tf_legacy_loss": false,
179
+ "tie_encoder_decoder": false,
180
+ "tie_word_embeddings": true,
181
+ "tokenizer_class": null,
182
+ "top_k": 50,
183
+ "top_p": 1.0,
184
+ "torch_dtype": null,
185
+ "torchscript": false,
186
+ "transformers_version": "4.37.1",
187
+ "typical_p": 1.0,
188
+ "use_bfloat16": false,
189
+ "vision_model_name_or_path": "google/siglip-so400m-patch14-384"
190
+ }
191
+ },
192
+ "vocab_size": 50296
193
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.38.2"
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebb540911159123e43b385e8092e66ee49867ec57fc2e7d4a1e8ac6f5c11e9e1
3
+ size 4992242256
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd437b42e2ae02b87b7a8b7105da5c129a5ca92362d64576b807c27de6436372
3
+ size 1935022780
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,336 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": " ",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "50258": {
22
+ "content": " ",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "50259": {
30
+ "content": " ",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "50260": {
38
+ "content": " ",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "50261": {
46
+ "content": " ",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "50262": {
54
+ "content": " ",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "50263": {
62
+ "content": " ",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "50264": {
70
+ "content": " ",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "50265": {
78
+ "content": " ",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "50266": {
86
+ "content": " ",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "50267": {
94
+ "content": " ",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "50268": {
102
+ "content": " ",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "50269": {
110
+ "content": " ",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "50270": {
118
+ "content": " ",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "50271": {
126
+ "content": " ",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "50272": {
134
+ "content": " ",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "50273": {
142
+ "content": " ",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "50274": {
150
+ "content": " ",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "50275": {
158
+ "content": " ",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "50276": {
166
+ "content": " ",
167
+ "lstrip": false,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "50277": {
174
+ "content": " ",
175
+ "lstrip": false,
176
+ "normalized": true,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "50278": {
182
+ "content": " ",
183
+ "lstrip": false,
184
+ "normalized": true,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "50279": {
190
+ "content": " ",
191
+ "lstrip": false,
192
+ "normalized": true,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "50280": {
198
+ "content": " ",
199
+ "lstrip": false,
200
+ "normalized": true,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "50281": {
206
+ "content": " ",
207
+ "lstrip": false,
208
+ "normalized": true,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "50282": {
214
+ "content": " ",
215
+ "lstrip": false,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "50283": {
222
+ "content": " ",
223
+ "lstrip": false,
224
+ "normalized": true,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "50284": {
230
+ "content": " ",
231
+ "lstrip": false,
232
+ "normalized": true,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "50285": {
238
+ "content": " ",
239
+ "lstrip": false,
240
+ "normalized": true,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "50286": {
246
+ "content": " ",
247
+ "lstrip": false,
248
+ "normalized": true,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "50287": {
254
+ "content": "\t\t\t\t\t\t\t\t\t",
255
+ "lstrip": false,
256
+ "normalized": true,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "50288": {
262
+ "content": "\t\t\t\t\t\t\t\t",
263
+ "lstrip": false,
264
+ "normalized": true,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "50289": {
270
+ "content": "\t\t\t\t\t\t\t",
271
+ "lstrip": false,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "50290": {
278
+ "content": "\t\t\t\t\t\t",
279
+ "lstrip": false,
280
+ "normalized": true,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "50291": {
286
+ "content": "\t\t\t\t\t",
287
+ "lstrip": false,
288
+ "normalized": true,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "50292": {
294
+ "content": "\t\t\t\t",
295
+ "lstrip": false,
296
+ "normalized": true,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "50293": {
302
+ "content": "\t\t\t",
303
+ "lstrip": false,
304
+ "normalized": true,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "50294": {
310
+ "content": "\t\t",
311
+ "lstrip": false,
312
+ "normalized": true,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "50295": {
318
+ "content": "[SEG]",
319
+ "lstrip": false,
320
+ "normalized": true,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ }
325
+ },
326
+ "bos_token": "<|endoftext|>",
327
+ "clean_up_tokenization_spaces": true,
328
+ "eos_token": "<|endoftext|>",
329
+ "errors": "replace",
330
+ "model_max_length": 2048,
331
+ "pad_token": "<|endoftext|>",
332
+ "padding_side": "right",
333
+ "split_special_tokens": false,
334
+ "tokenizer_class": "CodeGenTokenizer",
335
+ "unk_token": "<|endoftext|>"
336
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff