Hugging Face's logo

pallavibiswas
/
idefics2-finetuned-re-id

Safetensors
idefics2
Generated from Trainer
Model card Files Community
pallavibiswas commited on
Commit
b0c4c69
•
1 Parent(s): d0a8fe5

Upload config

Browse files
Files changed (2) hide show
  1. README.md +1 -1
  2. config.json +234 -0
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: apache-2.0
3
  base_model: HuggingFaceM4/idefics2-8b
 
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
1
  ---
 
2
  base_model: HuggingFaceM4/idefics2-8b
3
+ license: apache-2.0
4
  tags:
5
  - generated_from_trainer
6
  model-index:
config.json ADDED
@@ -0,0 +1,234 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceM4/idefics2-8b",
3
+ "architectures": [
4
+ "Idefics2ForConditionalGeneration"
5
+ ],
6
+ "image_token_id": 32001,
7
+ "model_type": "idefics2",
8
+ "perceiver_config": {
9
+ "_name_or_path": "",
10
+ "add_cross_attention": false,
11
+ "architectures": null,
12
+ "attention_dropout": 0.0,
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": "silu",
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "is_decoder": false,
34
+ "is_encoder_decoder": false,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1
38
+ },
39
+ "length_penalty": 1.0,
40
+ "max_length": 20,
41
+ "min_length": 0,
42
+ "model_type": "idefics2",
43
+ "no_repeat_ngram_size": 0,
44
+ "num_beam_groups": 1,
45
+ "num_beams": 1,
46
+ "num_key_value_heads": 4,
47
+ "num_return_sequences": 1,
48
+ "output_attentions": false,
49
+ "output_hidden_states": false,
50
+ "output_scores": false,
51
+ "pad_token_id": null,
52
+ "prefix": null,
53
+ "problem_type": null,
54
+ "pruned_heads": {},
55
+ "remove_invalid_values": false,
56
+ "repetition_penalty": 1.0,
57
+ "resampler_depth": 3,
58
+ "resampler_head_dim": 96,
59
+ "resampler_n_heads": 16,
60
+ "resampler_n_latents": 64,
61
+ "return_dict": true,
62
+ "return_dict_in_generate": false,
63
+ "sep_token_id": null,
64
+ "suppress_tokens": null,
65
+ "task_specific_params": null,
66
+ "temperature": 1.0,
67
+ "tf_legacy_loss": false,
68
+ "tie_encoder_decoder": false,
69
+ "tie_word_embeddings": true,
70
+ "tokenizer_class": null,
71
+ "top_k": 50,
72
+ "top_p": 1.0,
73
+ "torch_dtype": null,
74
+ "torchscript": false,
75
+ "typical_p": 1.0,
76
+ "use_bfloat16": false
77
+ },
78
+ "text_config": {
79
+ "_name_or_path": "",
80
+ "add_cross_attention": false,
81
+ "architectures": null,
82
+ "attention_dropout": 0.0,
83
+ "bad_words_ids": null,
84
+ "begin_suppress_tokens": null,
85
+ "bos_token_id": 1,
86
+ "chunk_size_feed_forward": 0,
87
+ "cross_attention_hidden_size": null,
88
+ "decoder_start_token_id": null,
89
+ "diversity_penalty": 0.0,
90
+ "do_sample": false,
91
+ "early_stopping": false,
92
+ "encoder_no_repeat_ngram_size": 0,
93
+ "eos_token_id": 2,
94
+ "exponential_decay_length_penalty": null,
95
+ "finetuning_task": null,
96
+ "forced_bos_token_id": null,
97
+ "forced_eos_token_id": null,
98
+ "head_dim": 128,
99
+ "hidden_act": "silu",
100
+ "hidden_size": 4096,
101
+ "id2label": {
102
+ "0": "LABEL_0",
103
+ "1": "LABEL_1"
104
+ },
105
+ "initializer_range": 0.02,
106
+ "intermediate_size": 14336,
107
+ "is_decoder": false,
108
+ "is_encoder_decoder": false,
109
+ "label2id": {
110
+ "LABEL_0": 0,
111
+ "LABEL_1": 1
112
+ },
113
+ "length_penalty": 1.0,
114
+ "max_length": 20,
115
+ "max_position_embeddings": 32768,
116
+ "min_length": 0,
117
+ "model_type": "mistral",
118
+ "no_repeat_ngram_size": 0,
119
+ "num_attention_heads": 32,
120
+ "num_beam_groups": 1,
121
+ "num_beams": 1,
122
+ "num_hidden_layers": 32,
123
+ "num_key_value_heads": 8,
124
+ "num_return_sequences": 1,
125
+ "output_attentions": false,
126
+ "output_hidden_states": false,
127
+ "output_scores": false,
128
+ "pad_token_id": 0,
129
+ "prefix": null,
130
+ "problem_type": null,
131
+ "pruned_heads": {},
132
+ "remove_invalid_values": false,
133
+ "repetition_penalty": 1.0,
134
+ "return_dict": true,
135
+ "return_dict_in_generate": false,
136
+ "rms_norm_eps": 1e-05,
137
+ "rope_theta": 10000.0,
138
+ "sep_token_id": null,
139
+ "sliding_window": 4096,
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": false,
146
+ "tokenizer_class": null,
147
+ "top_k": 50,
148
+ "top_p": 1.0,
149
+ "torch_dtype": null,
150
+ "torchscript": false,
151
+ "typical_p": 1.0,
152
+ "use_bfloat16": false,
153
+ "use_cache": true,
154
+ "vocab_size": 32003
155
+ },
156
+ "tie_word_embeddings": false,
157
+ "torch_dtype": "float32",
158
+ "transformers_version": "4.45.0.dev0",
159
+ "use_cache": true,
160
+ "vision_config": {
161
+ "_name_or_path": "",
162
+ "add_cross_attention": false,
163
+ "architectures": null,
164
+ "attention_dropout": 0.0,
165
+ "bad_words_ids": null,
166
+ "begin_suppress_tokens": null,
167
+ "bos_token_id": null,
168
+ "chunk_size_feed_forward": 0,
169
+ "cross_attention_hidden_size": null,
170
+ "decoder_start_token_id": null,
171
+ "diversity_penalty": 0.0,
172
+ "do_sample": false,
173
+ "early_stopping": false,
174
+ "encoder_no_repeat_ngram_size": 0,
175
+ "eos_token_id": null,
176
+ "exponential_decay_length_penalty": null,
177
+ "finetuning_task": null,
178
+ "forced_bos_token_id": null,
179
+ "forced_eos_token_id": null,
180
+ "hidden_act": "gelu_pytorch_tanh",
181
+ "hidden_size": 1152,
182
+ "id2label": {
183
+ "0": "LABEL_0",
184
+ "1": "LABEL_1"
185
+ },
186
+ "image_size": 980,
187
+ "initializer_range": 0.02,
188
+ "intermediate_size": 4304,
189
+ "is_decoder": false,
190
+ "is_encoder_decoder": false,
191
+ "label2id": {
192
+ "LABEL_0": 0,
193
+ "LABEL_1": 1
194
+ },
195
+ "layer_norm_eps": 1e-06,
196
+ "length_penalty": 1.0,
197
+ "max_length": 20,
198
+ "min_length": 0,
199
+ "model_type": "idefics2",
200
+ "no_repeat_ngram_size": 0,
201
+ "num_attention_heads": 16,
202
+ "num_beam_groups": 1,
203
+ "num_beams": 1,
204
+ "num_channels": 3,
205
+ "num_hidden_layers": 27,
206
+ "num_return_sequences": 1,
207
+ "output_attentions": false,
208
+ "output_hidden_states": false,
209
+ "output_scores": false,
210
+ "pad_token_id": null,
211
+ "patch_size": 14,
212
+ "prefix": null,
213
+ "problem_type": null,
214
+ "pruned_heads": {},
215
+ "remove_invalid_values": false,
216
+ "repetition_penalty": 1.0,
217
+ "return_dict": true,
218
+ "return_dict_in_generate": false,
219
+ "sep_token_id": null,
220
+ "suppress_tokens": null,
221
+ "task_specific_params": null,
222
+ "temperature": 1.0,
223
+ "tf_legacy_loss": false,
224
+ "tie_encoder_decoder": false,
225
+ "tie_word_embeddings": true,
226
+ "tokenizer_class": null,
227
+ "top_k": 50,
228
+ "top_p": 1.0,
229
+ "torch_dtype": null,
230
+ "torchscript": false,
231
+ "typical_p": 1.0,
232
+ "use_bfloat16": false
233
+ }
234
+ }