Hugging Face's logo

prithivMLmods
/
OpenSDI-SDXL-SigLIP2

Image Classification
Transformers
Safetensors
English
siglip
OpenSDI
Spotting Diffusion-Generated Images in the Open World
SDXL
AI-vs-Real
SigLIP2
Model card Files
xet
prithivMLmods commited on
Commit
5675947
·
verified ·
1 Parent(s): a8266f9

Upload folder using huggingface_hub

Browse files
Files changed (28) 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-1875/config.json +46 -0
  10. checkpoint-1875/model.safetensors +3 -0
  11. checkpoint-1875/optimizer.pt +3 -0
  12. checkpoint-1875/preprocessor_config.json +24 -0
  13. checkpoint-1875/rng_state.pth +3 -0
  14. checkpoint-1875/scheduler.pt +3 -0
  15. checkpoint-1875/trainer_state.json +85 -0
  16. checkpoint-1875/training_args.bin +3 -0
  17. checkpoint-625/config.json +46 -0
  18. checkpoint-625/model.safetensors +3 -0
  19. checkpoint-625/optimizer.pt +3 -0
  20. checkpoint-625/preprocessor_config.json +24 -0
  21. checkpoint-625/rng_state.pth +3 -0
  22. checkpoint-625/scheduler.pt +3 -0
  23. checkpoint-625/trainer_state.json +51 -0
  24. checkpoint-625/training_args.bin +3 -0
  25. config.json +46 -0
  26. model.safetensors +3 -0
  27. preprocessor_config.json +24 -0
  28. 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": "SDXL_Generated"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "Real_Image": 0,
12
+ "SDXL_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 sha256:6f434e36acfc8916b43d6deaed5fb88ee31402b80bb9eb2a06ef98e72c199692
3
+ size 371567992
checkpoint-1250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:047aa5116cc359a1768faf60a9526f8d95c85273d73076f6825bfc43d3ff3410
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:c3ff31f19a9702964373f2ff192ea7978653c7bf6d26f7cd94a4a72219e75924
3
+ size 1064
checkpoint-1250/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1250,
3
+ "best_metric": 0.33390238881111145,
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": 48.33537673950195,
15
+ "learning_rate": 1.5068493150684933e-05,
16
+ "loss": 0.5378,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.7981,
22
+ "eval_loss": 0.40214166045188904,
23
+ "eval_model_preparation_time": 0.0025,
24
+ "eval_runtime": 436.5615,
25
+ "eval_samples_per_second": 45.813,
26
+ "eval_steps_per_second": 5.727,
27
+ "step": 625
28
+ },
29
+ {
30
+ "epoch": 1.6,
31
+ "grad_norm": 28.126569747924805,
32
+ "learning_rate": 9.589041095890411e-06,
33
+ "loss": 0.4136,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.84045,
39
+ "eval_loss": 0.33390238881111145,
40
+ "eval_model_preparation_time": 0.0025,
41
+ "eval_runtime": 440.1327,
42
+ "eval_samples_per_second": 45.441,
43
+ "eval_steps_per_second": 5.68,
44
+ "step": 1250
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 1875,
49
+ "num_input_tokens_seen": 0,
50
+ "num_train_epochs": 3,
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": false
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 sha256:144bee43db531641a7b70cd74c8705660fdbba6b1fa956e35d64b4aa8773428a
3
+ size 5304
checkpoint-1875/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Real_Image",
7
+ "1": "SDXL_Generated"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "Real_Image": 0,
12
+ "SDXL_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-1875/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf36e1a50335a2a26dc81901fe09f9cb9327f6fbc86336e8fc078eb3e326a79b
3
+ size 371567992
checkpoint-1875/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1aa2f0478f6a409ef2b2d2dbdd48b7489a9339d537bbece5a8493ca448a86f1
3
+ size 686555770
checkpoint-1875/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-1875/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72f3bf471f7d501498c848c5bc931fdb3b46189bbc2a8c7e4dca5a1e3e186cbb
3
+ size 14244
checkpoint-1875/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4382e34b00b193a214af52d7c690641253d53262a9c9b98bc896a268172345a3
3
+ size 1064
checkpoint-1875/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1875,
3
+ "best_metric": 0.28406307101249695,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1875",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1875,
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": 48.33537673950195,
15
+ "learning_rate": 1.5068493150684933e-05,
16
+ "loss": 0.5378,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.7981,
22
+ "eval_loss": 0.40214166045188904,
23
+ "eval_model_preparation_time": 0.0025,
24
+ "eval_runtime": 436.5615,
25
+ "eval_samples_per_second": 45.813,
26
+ "eval_steps_per_second": 5.727,
27
+ "step": 625
28
+ },
29
+ {
30
+ "epoch": 1.6,
31
+ "grad_norm": 28.126569747924805,
32
+ "learning_rate": 9.589041095890411e-06,
33
+ "loss": 0.4136,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.84045,
39
+ "eval_loss": 0.33390238881111145,
40
+ "eval_model_preparation_time": 0.0025,
41
+ "eval_runtime": 440.1327,
42
+ "eval_samples_per_second": 45.441,
43
+ "eval_steps_per_second": 5.68,
44
+ "step": 1250
45
+ },
46
+ {
47
+ "epoch": 2.4,
48
+ "grad_norm": 25.899932861328125,
49
+ "learning_rate": 4.109589041095891e-06,
50
+ "loss": 0.3482,
51
+ "step": 1500
52
+ },
53
+ {
54
+ "epoch": 3.0,
55
+ "eval_accuracy": 0.86845,
56
+ "eval_loss": 0.28406307101249695,
57
+ "eval_model_preparation_time": 0.0025,
58
+ "eval_runtime": 433.8072,
59
+ "eval_samples_per_second": 46.103,
60
+ "eval_steps_per_second": 5.763,
61
+ "step": 1875
62
+ }
63
+ ],
64
+ "logging_steps": 500,
65
+ "max_steps": 1875,
66
+ "num_input_tokens_seen": 0,
67
+ "num_train_epochs": 3,
68
+ "save_steps": 500,
69
+ "stateful_callbacks": {
70
+ "TrainerControl": {
71
+ "args": {
72
+ "should_epoch_stop": false,
73
+ "should_evaluate": false,
74
+ "should_log": false,
75
+ "should_save": true,
76
+ "should_training_stop": true
77
+ },
78
+ "attributes": {}
79
+ }
80
+ },
81
+ "total_flos": 5.02532974927872e+18,
82
+ "train_batch_size": 32,
83
+ "trial_name": null,
84
+ "trial_params": null
85
+ }
checkpoint-1875/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:144bee43db531641a7b70cd74c8705660fdbba6b1fa956e35d64b4aa8773428a
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": "SDXL_Generated"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "Real_Image": 0,
12
+ "SDXL_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 sha256:14847ebbde088ca05e478522951bfc6adaecec792b8d53ed221a827bcd5914a7
3
+ size 371567992
checkpoint-625/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a69f0a970b348990de00b7061ab3caaf8eb6da85ebe709073a9dd83a97b5ee
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:a76475810944ec13e5c620f09ea3d88576275fcc605b1bf46e4648803eb72033
3
+ size 1064
checkpoint-625/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 625,
3
+ "best_metric": 0.40214166045188904,
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": 48.33537673950195,
15
+ "learning_rate": 1.5068493150684933e-05,
16
+ "loss": 0.5378,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.7981,
22
+ "eval_loss": 0.40214166045188904,
23
+ "eval_model_preparation_time": 0.0025,
24
+ "eval_runtime": 436.5615,
25
+ "eval_samples_per_second": 45.813,
26
+ "eval_steps_per_second": 5.727,
27
+ "step": 625
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 1875,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
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 sha256:144bee43db531641a7b70cd74c8705660fdbba6b1fa956e35d64b4aa8773428a
3
+ size 5304
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Real_Image",
7
+ "1": "SDXL_Generated"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "Real_Image": 0,
12
+ "SDXL_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:bf36e1a50335a2a26dc81901fe09f9cb9327f6fbc86336e8fc078eb3e326a79b
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 sha256:144bee43db531641a7b70cd74c8705660fdbba6b1fa956e35d64b4aa8773428a
3
+ size 5304