Hugging Face's logo

prithivMLmods
/
OpenSDI-SD2.1-SigLIP2

Image Classification
Transformers
Safetensors
English
siglip
OpenSDI
Spotting Diffusion-Generated Images in the Open World
AI-vs-Real
SigLIP2
SD2.1
Model card Files
xet
prithivMLmods commited on
Commit
c443301
·
verified ·
1 Parent(s): 64132c4

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. checkpoint-1250/config.json +46 -0
  2. checkpoint-1250/model.safetensors +3 -0
  3. checkpoint-1250/optimizer.pt +3 -0
  4. checkpoint-1250/preprocessor_config.json +24 -0
  5. checkpoint-1250/rng_state.pth +3 -0
  6. checkpoint-1250/scheduler.pt +3 -0
  7. checkpoint-1250/trainer_state.json +68 -0
  8. checkpoint-1250/training_args.bin +3 -0
  9. checkpoint-625/config.json +46 -0
  10. checkpoint-625/model.safetensors +3 -0
  11. checkpoint-625/optimizer.pt +3 -0
  12. checkpoint-625/preprocessor_config.json +24 -0
  13. checkpoint-625/rng_state.pth +3 -0
  14. checkpoint-625/scheduler.pt +3 -0
  15. checkpoint-625/trainer_state.json +51 -0
  16. checkpoint-625/training_args.bin +3 -0
  17. config.json +46 -0
  18. model.safetensors +3 -0
  19. preprocessor_config.json +24 -0
  20. training_args.bin +3 -0
checkpoint-1250/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Real_Image",
7
+ "1": "SD2.1_Generated"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "Real_Image": 0,
12
+ "SD2.1_Generated": 1
13
+ },
14
+ "model_type": "siglip",
15
+ "problem_type": "single_label_classification",
16
+ "text_config": {
17
+ "attention_dropout": 0.0,
18
+ "hidden_act": "gelu_pytorch_tanh",
19
+ "hidden_size": 768,
20
+ "intermediate_size": 3072,
21
+ "layer_norm_eps": 1e-06,
22
+ "max_position_embeddings": 64,
23
+ "model_type": "siglip_text_model",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "projection_size": 768,
27
+ "torch_dtype": "float32",
28
+ "vocab_size": 256000
29
+ },
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.50.0",
32
+ "vision_config": {
33
+ "attention_dropout": 0.0,
34
+ "hidden_act": "gelu_pytorch_tanh",
35
+ "hidden_size": 768,
36
+ "image_size": 224,
37
+ "intermediate_size": 3072,
38
+ "layer_norm_eps": 1e-06,
39
+ "model_type": "siglip_vision_model",
40
+ "num_attention_heads": 12,
41
+ "num_channels": 3,
42
+ "num_hidden_layers": 12,
43
+ "patch_size": 16,
44
+ "torch_dtype": "float32"
45
+ }
46
+ }
checkpoint-1250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02a01599aa7cdd11c97e431872b7c086dd3c19c7cd0d7bf0b73f39612a01273c
3
+ size 371567992
checkpoint-1250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50ce81c9cede6f135ec78d8124e5f7d2f984926b85efd7925b3f846fd35fbd3f
3
+ size 686555770
checkpoint-1250/preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "SiglipImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "SiglipProcessor",
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ }
24
+ }
checkpoint-1250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e47c81b882f33c5e2f4e777f5a233ce5a180fe1b81e4d6371f9de3fbb3170c
3
+ size 14244
checkpoint-1250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff845d3c5bd3a9f5a856f442525715cb4a3967d3f73353fd0847524d52bc8285
3
+ size 1064
checkpoint-1250/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1250,
3
+ "best_metric": 0.27138784527778625,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1250",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1250,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.8,
14
+ "grad_norm": 10.04687786102295,
15
+ "learning_rate": 1.25e-05,
16
+ "loss": 0.5283,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.82355,
22
+ "eval_loss": 0.3509272336959839,
23
+ "eval_model_preparation_time": 0.0024,
24
+ "eval_runtime": 400.2985,
25
+ "eval_samples_per_second": 49.963,
26
+ "eval_steps_per_second": 6.245,
27
+ "step": 625
28
+ },
29
+ {
30
+ "epoch": 1.6,
31
+ "grad_norm": 25.848796844482422,
32
+ "learning_rate": 4.166666666666667e-06,
33
+ "loss": 0.3737,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.8724,
39
+ "eval_loss": 0.27138784527778625,
40
+ "eval_model_preparation_time": 0.0024,
41
+ "eval_runtime": 392.0691,
42
+ "eval_samples_per_second": 51.011,
43
+ "eval_steps_per_second": 6.376,
44
+ "step": 1250
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 1250,
49
+ "num_input_tokens_seen": 0,
50
+ "num_train_epochs": 2,
51
+ "save_steps": 500,
52
+ "stateful_callbacks": {
53
+ "TrainerControl": {
54
+ "args": {
55
+ "should_epoch_stop": false,
56
+ "should_evaluate": false,
57
+ "should_log": false,
58
+ "should_save": true,
59
+ "should_training_stop": true
60
+ },
61
+ "attributes": {}
62
+ }
63
+ },
64
+ "total_flos": 3.35021983285248e+18,
65
+ "train_batch_size": 32,
66
+ "trial_name": null,
67
+ "trial_params": null
68
+ }
checkpoint-1250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec9d58a64dadc29e65d1386918b7a95f913c50a3482e59530781dfc23885cb7
3
+ size 5304
checkpoint-625/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Real_Image",
7
+ "1": "SD2.1_Generated"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "Real_Image": 0,
12
+ "SD2.1_Generated": 1
13
+ },
14
+ "model_type": "siglip",
15
+ "problem_type": "single_label_classification",
16
+ "text_config": {
17
+ "attention_dropout": 0.0,
18
+ "hidden_act": "gelu_pytorch_tanh",
19
+ "hidden_size": 768,
20
+ "intermediate_size": 3072,
21
+ "layer_norm_eps": 1e-06,
22
+ "max_position_embeddings": 64,
23
+ "model_type": "siglip_text_model",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "projection_size": 768,
27
+ "torch_dtype": "float32",
28
+ "vocab_size": 256000
29
+ },
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.50.0",
32
+ "vision_config": {
33
+ "attention_dropout": 0.0,
34
+ "hidden_act": "gelu_pytorch_tanh",
35
+ "hidden_size": 768,
36
+ "image_size": 224,
37
+ "intermediate_size": 3072,
38
+ "layer_norm_eps": 1e-06,
39
+ "model_type": "siglip_vision_model",
40
+ "num_attention_heads": 12,
41
+ "num_channels": 3,
42
+ "num_hidden_layers": 12,
43
+ "patch_size": 16,
44
+ "torch_dtype": "float32"
45
+ }
46
+ }
checkpoint-625/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc81e55c8a4dc7ed1bb5ac125cd5329216014edb2008f1ad1af41aa3ded411c2
3
+ size 371567992
checkpoint-625/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ecab4d3f090fe2ac6053c69686b82a6239bc5c4a896224f37b77d3905272684
3
+ size 686555770
checkpoint-625/preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "SiglipImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "SiglipProcessor",
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ }
24
+ }
checkpoint-625/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b97d2b074f45d2c8636b033e7029690ff74569ff4607f775707cdd593a86f2d8
3
+ size 14244
checkpoint-625/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1600002f41269d0a04dec00394845f17b20d0a04f16a163184ebb3c1f08f9f40
3
+ size 1064
checkpoint-625/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 625,
3
+ "best_metric": 0.3509272336959839,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-625",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 625,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.8,
14
+ "grad_norm": 10.04687786102295,
15
+ "learning_rate": 1.25e-05,
16
+ "loss": 0.5283,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.82355,
22
+ "eval_loss": 0.3509272336959839,
23
+ "eval_model_preparation_time": 0.0024,
24
+ "eval_runtime": 400.2985,
25
+ "eval_samples_per_second": 49.963,
26
+ "eval_steps_per_second": 6.245,
27
+ "step": 625
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 1250,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "stateful_callbacks": {
36
+ "TrainerControl": {
37
+ "args": {
38
+ "should_epoch_stop": false,
39
+ "should_evaluate": false,
40
+ "should_log": false,
41
+ "should_save": true,
42
+ "should_training_stop": false
43
+ },
44
+ "attributes": {}
45
+ }
46
+ },
47
+ "total_flos": 1.67510991642624e+18,
48
+ "train_batch_size": 32,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
checkpoint-625/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec9d58a64dadc29e65d1386918b7a95f913c50a3482e59530781dfc23885cb7
3
+ size 5304
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Real_Image",
7
+ "1": "SD2.1_Generated"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "Real_Image": 0,
12
+ "SD2.1_Generated": 1
13
+ },
14
+ "model_type": "siglip",
15
+ "problem_type": "single_label_classification",
16
+ "text_config": {
17
+ "attention_dropout": 0.0,
18
+ "hidden_act": "gelu_pytorch_tanh",
19
+ "hidden_size": 768,
20
+ "intermediate_size": 3072,
21
+ "layer_norm_eps": 1e-06,
22
+ "max_position_embeddings": 64,
23
+ "model_type": "siglip_text_model",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "projection_size": 768,
27
+ "torch_dtype": "float32",
28
+ "vocab_size": 256000
29
+ },
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.50.0",
32
+ "vision_config": {
33
+ "attention_dropout": 0.0,
34
+ "hidden_act": "gelu_pytorch_tanh",
35
+ "hidden_size": 768,
36
+ "image_size": 224,
37
+ "intermediate_size": 3072,
38
+ "layer_norm_eps": 1e-06,
39
+ "model_type": "siglip_vision_model",
40
+ "num_attention_heads": 12,
41
+ "num_channels": 3,
42
+ "num_hidden_layers": 12,
43
+ "patch_size": 16,
44
+ "torch_dtype": "float32"
45
+ }
46
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02a01599aa7cdd11c97e431872b7c086dd3c19c7cd0d7bf0b73f39612a01273c
3
+ size 371567992
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "SiglipImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "SiglipProcessor",
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ }
24
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec9d58a64dadc29e65d1386918b7a95f913c50a3482e59530781dfc23885cb7
3
+ size 5304