Hugging Face's logo

prithivMLmods
/
PussyCat-vs-Doggie-SigLIP2

Image Classification
Transformers
Safetensors
English
siglip
Cat
Dog
Classification
SigLIP2
Vision-encoder
Model card Files Community
prithivMLmods commited on
Commit
e2282b7
·
verified ·
1 Parent(s): da8a79b

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. checkpoint-1564/config.json +46 -0
  2. checkpoint-1564/model.safetensors +3 -0
  3. checkpoint-1564/optimizer.pt +3 -0
  4. checkpoint-1564/preprocessor_config.json +24 -0
  5. checkpoint-1564/rng_state.pth +3 -0
  6. checkpoint-1564/scheduler.pt +3 -0
  7. checkpoint-1564/trainer_state.json +75 -0
  8. checkpoint-1564/training_args.bin +3 -0
  9. checkpoint-2346/config.json +46 -0
  10. checkpoint-2346/model.safetensors +3 -0
  11. checkpoint-2346/optimizer.pt +3 -0
  12. checkpoint-2346/preprocessor_config.json +24 -0
  13. checkpoint-2346/rng_state.pth +3 -0
  14. checkpoint-2346/scheduler.pt +3 -0
  15. checkpoint-2346/trainer_state.json +92 -0
  16. checkpoint-2346/training_args.bin +3 -0
  17. checkpoint-782/config.json +46 -0
  18. checkpoint-782/model.safetensors +3 -0
  19. checkpoint-782/optimizer.pt +3 -0
  20. checkpoint-782/preprocessor_config.json +24 -0
  21. checkpoint-782/rng_state.pth +3 -0
  22. checkpoint-782/scheduler.pt +3 -0
  23. checkpoint-782/trainer_state.json +51 -0
  24. checkpoint-782/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-1564/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Pussy Cat",
7
+ "1": "Doggie"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "Doggie": 1,
12
+ "Pussy Cat": 0
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": "4.50.2",
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-1564/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdbea9be421b37bdda2de6c3408fbbf8ad2465634b81abfe5a82ac3c76ffd6d0
3
+ size 371567992
checkpoint-1564/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e1e28bdb2ad93f5b512ab7f5a1028af48f0d8e9d95f9982431a1e9de7b6eaf7
3
+ size 686555770
checkpoint-1564/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-1564/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ab3f2ecb17883e5b0f400a21cb6dbe05a811cea5cca7a9d203e9f3c9046a3ff
3
+ size 14244
checkpoint-1564/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d5b7f2855ab0ddb512e6a2ae8a68435933542eecc75559503569e3114b9b4f0
3
+ size 1064
checkpoint-1564/trainer_state.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1564,
3
+ "best_metric": 0.3568730354309082,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1564",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1564,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.639386189258312,
14
+ "grad_norm": 4.334684371948242,
15
+ "learning_rate": 0.000160801393728223,
16
+ "loss": 0.642,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.74792,
22
+ "eval_loss": 0.5220636129379272,
23
+ "eval_model_preparation_time": 0.0024,
24
+ "eval_runtime": 325.9979,
25
+ "eval_samples_per_second": 76.688,
26
+ "eval_steps_per_second": 9.586,
27
+ "step": 782
28
+ },
29
+ {
30
+ "epoch": 1.278772378516624,
31
+ "grad_norm": 6.341824054718018,
32
+ "learning_rate": 0.00011724738675958189,
33
+ "loss": 0.554,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 1.918158567774936,
38
+ "grad_norm": 3.435889482498169,
39
+ "learning_rate": 7.369337979094078e-05,
40
+ "loss": 0.4517,
41
+ "step": 1500
42
+ },
43
+ {
44
+ "epoch": 2.0,
45
+ "eval_accuracy": 0.8422,
46
+ "eval_loss": 0.3568730354309082,
47
+ "eval_model_preparation_time": 0.0024,
48
+ "eval_runtime": 325.7227,
49
+ "eval_samples_per_second": 76.752,
50
+ "eval_steps_per_second": 9.594,
51
+ "step": 1564
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 2346,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 3,
58
+ "save_steps": 500,
59
+ "stateful_callbacks": {
60
+ "TrainerControl": {
61
+ "args": {
62
+ "should_epoch_stop": false,
63
+ "should_evaluate": false,
64
+ "should_log": false,
65
+ "should_save": true,
66
+ "should_training_stop": false
67
+ },
68
+ "attributes": {}
69
+ }
70
+ },
71
+ "total_flos": 4.1877747910656e+18,
72
+ "train_batch_size": 32,
73
+ "trial_name": null,
74
+ "trial_params": null
75
+ }
checkpoint-1564/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031608eef21b8e8c0696c488c3665b7b1b2daf0aaa8c0056d17d616ca7842061
3
+ size 5304
checkpoint-2346/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Pussy Cat",
7
+ "1": "Doggie"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "Doggie": 1,
12
+ "Pussy Cat": 0
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": "4.50.2",
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-2346/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79fc29f28e9e9c7509a74773fe120f662df036017a9c54f5d502c1f2d52d26a
3
+ size 371567992
checkpoint-2346/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b40ac651e1d7884af696076527b4773236fa476f5d4c66b317c871e0569fd022
3
+ size 686555770
checkpoint-2346/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-2346/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:333e828db5f95d3629ed01e6028ddbcb2570be2386ba42fb2e1ce5d1d55f8c08
3
+ size 14244
checkpoint-2346/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f6fb6c04e83ad8c7e7774f50cfceed3bf90e6e42ded09b4deef26723be76bc
3
+ size 1064
checkpoint-2346/trainer_state.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2346,
3
+ "best_metric": 0.24125342071056366,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-2346",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2346,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.639386189258312,
14
+ "grad_norm": 4.334684371948242,
15
+ "learning_rate": 0.000160801393728223,
16
+ "loss": 0.642,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.74792,
22
+ "eval_loss": 0.5220636129379272,
23
+ "eval_model_preparation_time": 0.0024,
24
+ "eval_runtime": 325.9979,
25
+ "eval_samples_per_second": 76.688,
26
+ "eval_steps_per_second": 9.586,
27
+ "step": 782
28
+ },
29
+ {
30
+ "epoch": 1.278772378516624,
31
+ "grad_norm": 6.341824054718018,
32
+ "learning_rate": 0.00011724738675958189,
33
+ "loss": 0.554,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 1.918158567774936,
38
+ "grad_norm": 3.435889482498169,
39
+ "learning_rate": 7.369337979094078e-05,
40
+ "loss": 0.4517,
41
+ "step": 1500
42
+ },
43
+ {
44
+ "epoch": 2.0,
45
+ "eval_accuracy": 0.8422,
46
+ "eval_loss": 0.3568730354309082,
47
+ "eval_model_preparation_time": 0.0024,
48
+ "eval_runtime": 325.7227,
49
+ "eval_samples_per_second": 76.752,
50
+ "eval_steps_per_second": 9.594,
51
+ "step": 1564
52
+ },
53
+ {
54
+ "epoch": 2.557544757033248,
55
+ "grad_norm": 3.6960785388946533,
56
+ "learning_rate": 3.0139372822299655e-05,
57
+ "loss": 0.3612,
58
+ "step": 2000
59
+ },
60
+ {
61
+ "epoch": 3.0,
62
+ "eval_accuracy": 0.89892,
63
+ "eval_loss": 0.24125342071056366,
64
+ "eval_model_preparation_time": 0.0024,
65
+ "eval_runtime": 325.5685,
66
+ "eval_samples_per_second": 76.789,
67
+ "eval_steps_per_second": 9.599,
68
+ "step": 2346
69
+ }
70
+ ],
71
+ "logging_steps": 500,
72
+ "max_steps": 2346,
73
+ "num_input_tokens_seen": 0,
74
+ "num_train_epochs": 3,
75
+ "save_steps": 500,
76
+ "stateful_callbacks": {
77
+ "TrainerControl": {
78
+ "args": {
79
+ "should_epoch_stop": false,
80
+ "should_evaluate": false,
81
+ "should_log": false,
82
+ "should_save": true,
83
+ "should_training_stop": true
84
+ },
85
+ "attributes": {}
86
+ }
87
+ },
88
+ "total_flos": 6.2816621865984e+18,
89
+ "train_batch_size": 32,
90
+ "trial_name": null,
91
+ "trial_params": null
92
+ }
checkpoint-2346/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031608eef21b8e8c0696c488c3665b7b1b2daf0aaa8c0056d17d616ca7842061
3
+ size 5304
checkpoint-782/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Pussy Cat",
7
+ "1": "Doggie"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "Doggie": 1,
12
+ "Pussy Cat": 0
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": "4.50.2",
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-782/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22aac27f046d479b9762ea9d01039ba4826525c7102c26acdd4e994fa4799e6b
3
+ size 371567992
checkpoint-782/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c8475d92e97e333710481bd6810ed5c51ec84ba5370ad7417dc61e4cc052ab
3
+ size 686555770
checkpoint-782/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-782/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25cf2ffbe4a7f760ce5228c6db114885fc5abd2f9ca0dce39616f33aa0d4b109
3
+ size 14244
checkpoint-782/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e7c83f1945c48f2c53fd17fcde3d15becda07dc54bc6bcabe436c1cf2fbc95
3
+ size 1064
checkpoint-782/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 782,
3
+ "best_metric": 0.5220636129379272,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-782",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 782,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.639386189258312,
14
+ "grad_norm": 4.334684371948242,
15
+ "learning_rate": 0.000160801393728223,
16
+ "loss": 0.642,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.74792,
22
+ "eval_loss": 0.5220636129379272,
23
+ "eval_model_preparation_time": 0.0024,
24
+ "eval_runtime": 325.9979,
25
+ "eval_samples_per_second": 76.688,
26
+ "eval_steps_per_second": 9.586,
27
+ "step": 782
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 2346,
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": 2.0938873955328e+18,
48
+ "train_batch_size": 32,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
checkpoint-782/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031608eef21b8e8c0696c488c3665b7b1b2daf0aaa8c0056d17d616ca7842061
3
+ size 5304
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Pussy Cat",
7
+ "1": "Doggie"
8
+ },
9
+ "initializer_factor": 1.0,
10
+ "label2id": {
11
+ "Doggie": 1,
12
+ "Pussy Cat": 0
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": "4.50.2",
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:b79fc29f28e9e9c7509a74773fe120f662df036017a9c54f5d502c1f2d52d26a
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 sha256:031608eef21b8e8c0696c488c3665b7b1b2daf0aaa8c0056d17d616ca7842061
3
+ size 5304