J-LAB commited on
Commit
fc17b13
1 Parent(s): d5f5f66

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +66 -218
config.json CHANGED
@@ -1,237 +1,85 @@
1
  {
2
- "_name_or_path": "microsoft/Florence-2-large",
3
  "architectures": [
4
  "Florence2ForConditionalGeneration"
5
  ],
6
  "auto_map": {
7
- "AutoConfig": "microsoft/Florence-2-large--configuration_florence2.Florence2Config",
8
- "AutoModelForCausalLM": "microsoft/Florence-2-large--modeling_florence2.Florence2ForConditionalGeneration"
9
  },
10
  "bos_token_id": 0,
11
  "eos_token_id": 2,
12
  "ignore_index": -100,
13
- "is_encoder_decoder": true,
14
  "model_type": "florence2",
15
  "pad_token_id": 1,
16
  "projection_dim": 1024,
17
  "text_config": {
18
- "_name_or_path": "",
19
- "activation_dropout": 0.1,
20
- "activation_function": "gelu",
21
- "add_bias_logits": false,
22
- "add_cross_attention": false,
23
- "add_final_layer_norm": false,
24
- "architectures": null,
25
- "attention_dropout": 0.1,
26
- "bad_words_ids": null,
27
- "begin_suppress_tokens": null,
28
- "bos_token_id": 0,
29
- "chunk_size_feed_forward": 0,
30
- "classif_dropout": 0.1,
31
- "classifier_dropout": 0.0,
32
- "cross_attention_hidden_size": null,
33
- "d_model": 1024,
34
- "decoder_attention_heads": 16,
35
- "decoder_ffn_dim": 4096,
36
- "decoder_layerdrop": 0.0,
37
- "decoder_layers": 12,
38
- "decoder_start_token_id": 2,
39
- "diversity_penalty": 0.0,
40
- "do_sample": false,
41
- "dropout": 0.1,
42
- "early_stopping": true,
43
- "encoder_attention_heads": 16,
44
- "encoder_ffn_dim": 4096,
45
- "encoder_layerdrop": 0.0,
46
- "encoder_layers": 12,
47
- "encoder_no_repeat_ngram_size": 0,
48
- "eos_token_id": 2,
49
- "exponential_decay_length_penalty": null,
50
- "finetuning_task": null,
51
- "forced_bos_token_id": 0,
52
- "forced_eos_token_id": 2,
53
- "gradient_checkpointing": false,
54
- "id2label": {
55
- "0": "LABEL_0",
56
- "1": "LABEL_1",
57
- "2": "LABEL_2"
58
- },
59
- "init_std": 0.02,
60
- "is_decoder": false,
61
- "is_encoder_decoder": true,
62
- "label2id": {
63
- "LABEL_0": 0,
64
- "LABEL_1": 1,
65
- "LABEL_2": 2
66
- },
67
- "length_penalty": 1.0,
68
- "max_length": 20,
69
- "max_position_embeddings": 1024,
70
- "min_length": 0,
71
- "model_type": "florence2_language",
72
- "no_repeat_ngram_size": 3,
73
- "normalize_before": false,
74
- "num_beam_groups": 1,
75
- "num_beams": 3,
76
- "num_hidden_layers": 12,
77
- "num_return_sequences": 1,
78
- "output_attentions": false,
79
- "output_hidden_states": false,
80
- "output_scores": false,
81
- "pad_token_id": 1,
82
- "prefix": null,
83
- "problem_type": null,
84
- "pruned_heads": {},
85
- "remove_invalid_values": false,
86
- "repetition_penalty": 1.0,
87
- "return_dict": true,
88
- "return_dict_in_generate": false,
89
- "scale_embedding": false,
90
- "sep_token_id": null,
91
- "suppress_tokens": null,
92
- "task_specific_params": null,
93
- "temperature": 1.0,
94
- "tf_legacy_loss": false,
95
- "tie_encoder_decoder": false,
96
- "tie_word_embeddings": true,
97
- "tokenizer_class": null,
98
- "top_k": 50,
99
- "top_p": 1.0,
100
- "torch_dtype": null,
101
- "torchscript": false,
102
- "typical_p": 1.0,
103
- "use_bfloat16": false,
104
- "use_cache": true,
105
- "vocab_size": 51289
106
  },
107
- "torch_dtype": "float32",
108
- "transformers_version": "4.42.4",
109
  "vision_config": {
110
- "_name_or_path": "",
111
- "add_cross_attention": false,
112
- "architectures": null,
113
- "bad_words_ids": null,
114
- "begin_suppress_tokens": null,
115
- "bos_token_id": null,
116
- "chunk_size_feed_forward": 0,
117
- "cross_attention_hidden_size": null,
118
- "decoder_start_token_id": null,
119
- "depths": [
120
- 1,
121
- 1,
122
- 9,
123
- 1
124
- ],
125
- "dim_embed": [
126
- 256,
127
- 512,
128
- 1024,
129
- 2048
130
- ],
131
- "diversity_penalty": 0.0,
132
- "do_sample": false,
133
- "drop_path_rate": 0.1,
134
- "early_stopping": false,
135
- "enable_checkpoint": false,
136
- "encoder_no_repeat_ngram_size": 0,
137
- "eos_token_id": null,
138
- "exponential_decay_length_penalty": null,
139
- "finetuning_task": null,
140
- "forced_bos_token_id": null,
141
- "forced_eos_token_id": null,
142
- "id2label": {
143
- "0": "LABEL_0",
144
- "1": "LABEL_1"
145
- },
146
- "image_feature_source": [
147
- "spatial_avg_pool",
148
- "temporal_avg_pool"
149
- ],
150
- "image_pos_embed": {
151
- "max_pos_embeddings": 50,
152
- "type": "learned_abs_2d"
153
- },
154
- "is_decoder": false,
155
- "is_encoder_decoder": false,
156
- "label2id": {
157
- "LABEL_0": 0,
158
- "LABEL_1": 1
159
- },
160
- "length_penalty": 1.0,
161
- "max_length": 20,
162
- "min_length": 0,
163
- "model_type": "",
164
- "no_repeat_ngram_size": 0,
165
- "num_beam_groups": 1,
166
- "num_beams": 1,
167
- "num_groups": [
168
- 8,
169
- 16,
170
- 32,
171
- 64
172
- ],
173
- "num_heads": [
174
- 8,
175
- 16,
176
- 32,
177
- 64
178
- ],
179
- "num_return_sequences": 1,
180
- "output_attentions": false,
181
- "output_hidden_states": false,
182
- "output_scores": false,
183
- "pad_token_id": null,
184
- "patch_padding": [
185
- 3,
186
- 1,
187
- 1,
188
- 1
189
- ],
190
- "patch_prenorm": [
191
- false,
192
- true,
193
- true,
194
- true
195
- ],
196
- "patch_size": [
197
- 7,
198
- 3,
199
- 3,
200
- 3
201
- ],
202
- "patch_stride": [
203
- 4,
204
- 2,
205
- 2,
206
- 2
207
- ],
208
- "prefix": null,
209
- "problem_type": null,
210
  "projection_dim": 1024,
211
- "pruned_heads": {},
212
- "remove_invalid_values": false,
213
- "repetition_penalty": 1.0,
214
- "return_dict": true,
215
- "return_dict_in_generate": false,
216
- "sep_token_id": null,
217
- "suppress_tokens": null,
218
- "task_specific_params": null,
219
- "temperature": 1.0,
220
- "tf_legacy_loss": false,
221
- "tie_encoder_decoder": false,
222
- "tie_word_embeddings": true,
223
- "tokenizer_class": null,
224
- "top_k": 50,
225
- "top_p": 1.0,
226
- "torch_dtype": null,
227
- "torchscript": false,
228
- "typical_p": 1.0,
229
- "use_bfloat16": false,
230
  "visual_temporal_embedding": {
231
- "max_temporal_embeddings": 100,
232
- "type": "COSINE"
233
  },
234
- "window_size": 12
 
 
 
 
235
  },
236
- "vocab_size": 51289
237
- }
 
 
 
 
1
  {
2
+ "_name_or_path": "florence2",
3
  "architectures": [
4
  "Florence2ForConditionalGeneration"
5
  ],
6
  "auto_map": {
7
+ "AutoConfig": "configuration_florence2.Florence2Config",
8
+ "AutoModelForCausalLM": "modeling_florence2.Florence2ForConditionalGeneration"
9
  },
10
  "bos_token_id": 0,
11
  "eos_token_id": 2,
12
  "ignore_index": -100,
 
13
  "model_type": "florence2",
14
  "pad_token_id": 1,
15
  "projection_dim": 1024,
16
  "text_config": {
17
+ "vocab_size": 51289,
18
+ "activation_dropout": 0.1,
19
+ "activation_function": "gelu",
20
+ "add_bias_logits": false,
21
+ "add_final_layer_norm": false,
22
+ "attention_dropout": 0.1,
23
+ "bos_token_id": 0,
24
+ "classif_dropout": 0.1,
25
+ "classifier_dropout": 0.0,
26
+ "d_model": 1024,
27
+ "decoder_attention_heads": 16,
28
+ "decoder_ffn_dim": 4096,
29
+ "decoder_layerdrop": 0.0,
30
+ "decoder_layers": 12,
31
+ "decoder_start_token_id": 2,
32
+ "dropout": 0.1,
33
+ "early_stopping": true,
34
+ "encoder_attention_heads": 16,
35
+ "encoder_ffn_dim": 4096,
36
+ "encoder_layerdrop": 0.0,
37
+ "encoder_layers": 12,
38
+ "eos_token_id": 2,
39
+ "forced_eos_token_id": 2,
40
+ "forced_bos_token_id": 0,
41
+ "gradient_checkpointing": false,
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "label2id": {
45
+ "LABEL_0": 0,
46
+ "LABEL_1": 1,
47
+ "LABEL_2": 2
48
+ },
49
+ "max_position_embeddings": 1024,
50
+ "no_repeat_ngram_size": 3,
51
+ "normalize_before": false,
52
+ "num_hidden_layers": 12,
53
+ "pad_token_id": 1,
54
+ "scale_embedding": false,
55
+ "num_beams": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
  },
 
 
57
  "vision_config": {
58
+ "model_type": "davit",
59
+ "drop_path_rate": 0.1,
60
+ "patch_size": [7, 3, 3, 3],
61
+ "patch_stride": [4, 2, 2, 2],
62
+ "patch_padding": [3, 1, 1, 1],
63
+ "patch_prenorm": [false, true, true, true],
64
+ "enable_checkpoint": false,
65
+ "dim_embed": [256, 512, 1024, 2048],
66
+ "num_heads": [8, 16, 32, 64],
67
+ "num_groups": [8, 16, 32, 64],
68
+ "depths": [1, 1, 9, 1],
69
+ "window_size": 12,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
  "projection_dim": 1024,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
  "visual_temporal_embedding": {
72
+ "type": "COSINE",
73
+ "max_temporal_embeddings": 100
74
  },
75
+ "image_pos_embed": {
76
+ "type": "learned_abs_2d",
77
+ "max_pos_embeddings": 50
78
+ },
79
+ "image_feature_source": ["spatial_avg_pool", "temporal_avg_pool"]
80
  },
81
+ "vocab_size": 51289,
82
+ "torch_dtype": "float32",
83
+ "transformers_version": "4.41.0.dev0",
84
+ "is_encoder_decoder": true
85
+ }