Hugging Face's logo

wyu1
/
Leopard-Idefics2

Safetensors
idefics2
Model card Files Community
wyu1 commited on
Commit
05fcd3d
•
1 Parent(s): 13a53bc

Add Leopard-Idefics2

Browse files
Files changed (1) hide show
  1. config.json +232 -0
config.json ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Idefics2ForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 32001,
6
+ "model_type": "idefics2",
7
+ "perceiver_config": {
8
+ "_name_or_path": "",
9
+ "add_cross_attention": false,
10
+ "architectures": null,
11
+ "attention_dropout": 0.0,
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": "silu",
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1"
31
+ },
32
+ "is_decoder": false,
33
+ "is_encoder_decoder": false,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1
37
+ },
38
+ "length_penalty": 1.0,
39
+ "max_length": 20,
40
+ "min_length": 0,
41
+ "model_type": "idefics2",
42
+ "no_repeat_ngram_size": 0,
43
+ "num_beam_groups": 1,
44
+ "num_beams": 1,
45
+ "num_key_value_heads": 16,
46
+ "num_return_sequences": 1,
47
+ "output_attentions": false,
48
+ "output_hidden_states": false,
49
+ "output_scores": false,
50
+ "pad_token_id": null,
51
+ "prefix": null,
52
+ "problem_type": null,
53
+ "pruned_heads": {},
54
+ "remove_invalid_values": false,
55
+ "repetition_penalty": 1.0,
56
+ "resampler_depth": 3,
57
+ "resampler_head_dim": 96,
58
+ "resampler_n_heads": 16,
59
+ "resampler_n_latents": 64,
60
+ "return_dict": true,
61
+ "return_dict_in_generate": false,
62
+ "sep_token_id": null,
63
+ "suppress_tokens": null,
64
+ "task_specific_params": null,
65
+ "temperature": 1.0,
66
+ "tf_legacy_loss": false,
67
+ "tie_encoder_decoder": false,
68
+ "tie_word_embeddings": true,
69
+ "tokenizer_class": null,
70
+ "top_k": 50,
71
+ "top_p": 1.0,
72
+ "torch_dtype": null,
73
+ "torchscript": false,
74
+ "typical_p": 1.0,
75
+ "use_bfloat16": false
76
+ },
77
+ "text_config": {
78
+ "_name_or_path": "",
79
+ "add_cross_attention": false,
80
+ "architectures": null,
81
+ "attention_dropout": 0.0,
82
+ "bad_words_ids": null,
83
+ "begin_suppress_tokens": null,
84
+ "bos_token_id": 1,
85
+ "chunk_size_feed_forward": 0,
86
+ "cross_attention_hidden_size": null,
87
+ "decoder_start_token_id": null,
88
+ "diversity_penalty": 0.0,
89
+ "do_sample": false,
90
+ "early_stopping": false,
91
+ "encoder_no_repeat_ngram_size": 0,
92
+ "eos_token_id": 2,
93
+ "exponential_decay_length_penalty": null,
94
+ "finetuning_task": null,
95
+ "forced_bos_token_id": null,
96
+ "forced_eos_token_id": null,
97
+ "hidden_act": "silu",
98
+ "hidden_size": 4096,
99
+ "id2label": {
100
+ "0": "LABEL_0",
101
+ "1": "LABEL_1"
102
+ },
103
+ "initializer_range": 0.02,
104
+ "intermediate_size": 14336,
105
+ "is_decoder": false,
106
+ "is_encoder_decoder": false,
107
+ "label2id": {
108
+ "LABEL_0": 0,
109
+ "LABEL_1": 1
110
+ },
111
+ "length_penalty": 1.0,
112
+ "max_length": 20,
113
+ "max_position_embeddings": 32768,
114
+ "min_length": 0,
115
+ "model_type": "mistral",
116
+ "no_repeat_ngram_size": 0,
117
+ "num_attention_heads": 32,
118
+ "num_beam_groups": 1,
119
+ "num_beams": 1,
120
+ "num_hidden_layers": 32,
121
+ "num_key_value_heads": 8,
122
+ "num_return_sequences": 1,
123
+ "output_attentions": false,
124
+ "output_hidden_states": false,
125
+ "output_scores": false,
126
+ "pad_token_id": 0,
127
+ "prefix": null,
128
+ "problem_type": null,
129
+ "pruned_heads": {},
130
+ "remove_invalid_values": false,
131
+ "repetition_penalty": 1.0,
132
+ "return_dict": true,
133
+ "return_dict_in_generate": false,
134
+ "rms_norm_eps": 1e-05,
135
+ "rope_theta": 10000.0,
136
+ "sep_token_id": null,
137
+ "sliding_window": 4096,
138
+ "suppress_tokens": null,
139
+ "task_specific_params": null,
140
+ "temperature": 1.0,
141
+ "tf_legacy_loss": false,
142
+ "tie_encoder_decoder": false,
143
+ "tie_word_embeddings": false,
144
+ "tokenizer_class": null,
145
+ "top_k": 50,
146
+ "top_p": 1.0,
147
+ "torch_dtype": null,
148
+ "torchscript": false,
149
+ "typical_p": 1.0,
150
+ "use_bfloat16": false,
151
+ "use_cache": true,
152
+ "vocab_size": 32003
153
+ },
154
+ "tie_word_embeddings": false,
155
+ "torch_dtype": "float32",
156
+ "transformers_version": "4.42.0",
157
+ "use_cache": true,
158
+ "vision_config": {
159
+ "_name_or_path": "",
160
+ "add_cross_attention": false,
161
+ "architectures": null,
162
+ "attention_dropout": 0.0,
163
+ "bad_words_ids": null,
164
+ "begin_suppress_tokens": null,
165
+ "bos_token_id": null,
166
+ "chunk_size_feed_forward": 0,
167
+ "cross_attention_hidden_size": null,
168
+ "decoder_start_token_id": null,
169
+ "diversity_penalty": 0.0,
170
+ "do_sample": false,
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
+ "hidden_act": "gelu_pytorch_tanh",
179
+ "hidden_size": 1152,
180
+ "id2label": {
181
+ "0": "LABEL_0",
182
+ "1": "LABEL_1"
183
+ },
184
+ "image_size": 980,
185
+ "initializer_range": 0.02,
186
+ "intermediate_size": 4304,
187
+ "is_decoder": false,
188
+ "is_encoder_decoder": false,
189
+ "label2id": {
190
+ "LABEL_0": 0,
191
+ "LABEL_1": 1
192
+ },
193
+ "layer_norm_eps": 1e-06,
194
+ "length_penalty": 1.0,
195
+ "max_length": 20,
196
+ "min_length": 0,
197
+ "model_type": "idefics2",
198
+ "no_repeat_ngram_size": 0,
199
+ "num_attention_heads": 16,
200
+ "num_beam_groups": 1,
201
+ "num_beams": 1,
202
+ "num_channels": 3,
203
+ "num_hidden_layers": 27,
204
+ "num_return_sequences": 1,
205
+ "output_attentions": false,
206
+ "output_hidden_states": false,
207
+ "output_scores": false,
208
+ "pad_token_id": null,
209
+ "patch_size": 14,
210
+ "prefix": null,
211
+ "problem_type": null,
212
+ "pruned_heads": {},
213
+ "remove_invalid_values": false,
214
+ "repetition_penalty": 1.0,
215
+ "return_dict": true,
216
+ "return_dict_in_generate": false,
217
+ "sep_token_id": null,
218
+ "suppress_tokens": null,
219
+ "task_specific_params": null,
220
+ "temperature": 1.0,
221
+ "tf_legacy_loss": false,
222
+ "tie_encoder_decoder": false,
223
+ "tie_word_embeddings": true,
224
+ "tokenizer_class": null,
225
+ "top_k": 50,
226
+ "top_p": 1.0,
227
+ "torch_dtype": null,
228
+ "torchscript": false,
229
+ "typical_p": 1.0,
230
+ "use_bfloat16": false
231
+ }
232
+ }