prithivMLmods commited on
Commit
ceed7df
·
verified ·
1 Parent(s): ae1ec41

Upload folder using huggingface_hub

Browse files
checkpoint-1656/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Anime Picture",
7
+ "1": "Hentai",
8
+ "2": "Neutral",
9
+ "3": "Pornography",
10
+ "4": "Enticing or Sensual"
11
+ },
12
+ "initializer_factor": 1.0,
13
+ "label2id": {
14
+ "Anime Picture": 0,
15
+ "Enticing or Sensual": 4,
16
+ "Hentai": 1,
17
+ "Neutral": 2,
18
+ "Pornography": 3
19
+ },
20
+ "model_type": "siglip",
21
+ "problem_type": "single_label_classification",
22
+ "text_config": {
23
+ "attention_dropout": 0.0,
24
+ "hidden_act": "gelu_pytorch_tanh",
25
+ "hidden_size": 768,
26
+ "intermediate_size": 3072,
27
+ "layer_norm_eps": 1e-06,
28
+ "max_position_embeddings": 64,
29
+ "model_type": "siglip_text_model",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "projection_size": 768,
33
+ "torch_dtype": "float32",
34
+ "vocab_size": 256000
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.50.3",
38
+ "vision_config": {
39
+ "attention_dropout": 0.0,
40
+ "hidden_act": "gelu_pytorch_tanh",
41
+ "hidden_size": 768,
42
+ "image_size": 224,
43
+ "intermediate_size": 3072,
44
+ "layer_norm_eps": 1e-06,
45
+ "model_type": "siglip_vision_model",
46
+ "num_attention_heads": 12,
47
+ "num_channels": 3,
48
+ "num_hidden_layers": 12,
49
+ "patch_size": 16,
50
+ "torch_dtype": "float32"
51
+ }
52
+ }
checkpoint-1656/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2624cb49f92884d9d3f9ec08e4f2016cd3a0611282526a81cdf6ec43a256b452
3
+ size 371577220
checkpoint-1656/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f12e5a4c5247415b1810bc35c47a7809a3b5733ceaaf36aa076e5c5066050ca0
3
+ size 686574202
checkpoint-1656/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-1656/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b395f57c7ddce57e9ef1719606f78ac267efd46ac9e0cacd7f473229ff44b2
3
+ size 14244
checkpoint-1656/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36413dbf261f7cb777a54f63f9ab46bddc0a62cf577b96d1b5ecb63ca861f54
3
+ size 1064
checkpoint-1656/trainer_state.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1656,
3
+ "best_metric": 0.5553735494613647,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1656",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1656,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.6038647342995169,
14
+ "grad_norm": 3.9172444343566895,
15
+ "learning_rate": 0.00016302382908792113,
16
+ "loss": 1.1039,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.7029792697201979,
22
+ "eval_loss": 0.7443631291389465,
23
+ "eval_model_preparation_time": 0.0023,
24
+ "eval_runtime": 481.4814,
25
+ "eval_samples_per_second": 55.003,
26
+ "eval_steps_per_second": 6.877,
27
+ "step": 828
28
+ },
29
+ {
30
+ "epoch": 1.2077294685990339,
31
+ "grad_norm": 4.54465913772583,
32
+ "learning_rate": 0.00012193919474116682,
33
+ "loss": 0.8238,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 1.8115942028985508,
38
+ "grad_norm": 9.120803833007812,
39
+ "learning_rate": 8.08545603944125e-05,
40
+ "loss": 0.71,
41
+ "step": 1500
42
+ },
43
+ {
44
+ "epoch": 2.0,
45
+ "eval_accuracy": 0.785258467696258,
46
+ "eval_loss": 0.5553735494613647,
47
+ "eval_model_preparation_time": 0.0023,
48
+ "eval_runtime": 482.7837,
49
+ "eval_samples_per_second": 54.855,
50
+ "eval_steps_per_second": 6.858,
51
+ "step": 1656
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 2484,
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": 4.436303952083448e+18,
72
+ "train_batch_size": 32,
73
+ "trial_name": null,
74
+ "trial_params": null
75
+ }
checkpoint-1656/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77f0ca87b3994c04b4f018469a0d2842d64d1c9897f79e494161c2d4afdb6510
3
+ size 5304
checkpoint-2484/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Anime Picture",
7
+ "1": "Hentai",
8
+ "2": "Neutral",
9
+ "3": "Pornography",
10
+ "4": "Enticing or Sensual"
11
+ },
12
+ "initializer_factor": 1.0,
13
+ "label2id": {
14
+ "Anime Picture": 0,
15
+ "Enticing or Sensual": 4,
16
+ "Hentai": 1,
17
+ "Neutral": 2,
18
+ "Pornography": 3
19
+ },
20
+ "model_type": "siglip",
21
+ "problem_type": "single_label_classification",
22
+ "text_config": {
23
+ "attention_dropout": 0.0,
24
+ "hidden_act": "gelu_pytorch_tanh",
25
+ "hidden_size": 768,
26
+ "intermediate_size": 3072,
27
+ "layer_norm_eps": 1e-06,
28
+ "max_position_embeddings": 64,
29
+ "model_type": "siglip_text_model",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "projection_size": 768,
33
+ "torch_dtype": "float32",
34
+ "vocab_size": 256000
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.50.3",
38
+ "vision_config": {
39
+ "attention_dropout": 0.0,
40
+ "hidden_act": "gelu_pytorch_tanh",
41
+ "hidden_size": 768,
42
+ "image_size": 224,
43
+ "intermediate_size": 3072,
44
+ "layer_norm_eps": 1e-06,
45
+ "model_type": "siglip_vision_model",
46
+ "num_attention_heads": 12,
47
+ "num_channels": 3,
48
+ "num_hidden_layers": 12,
49
+ "patch_size": 16,
50
+ "torch_dtype": "float32"
51
+ }
52
+ }
checkpoint-2484/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b56c9793be0162dfaf7662ab6ef9fc38c03a3533880a8ed98b3039c203a3865
3
+ size 371577220
checkpoint-2484/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bc4cc3f1ec50f533bf68d44fffd1b114dc67195b8b85290c462294d4080121a
3
+ size 686574202
checkpoint-2484/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-2484/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb29b7c6a866f78a6e6f730e82046110f1d35524684caefafa3a275ca50bfa2f
3
+ size 14244
checkpoint-2484/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a31cd561974c7aead3f0b38102c4adb619c7f4068c4fa44e62eeeec961a0e2cd
3
+ size 1064
checkpoint-2484/trainer_state.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2484,
3
+ "best_metric": 0.43748077750205994,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-2484",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2484,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.6038647342995169,
14
+ "grad_norm": 3.9172444343566895,
15
+ "learning_rate": 0.00016302382908792113,
16
+ "loss": 1.1039,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.7029792697201979,
22
+ "eval_loss": 0.7443631291389465,
23
+ "eval_model_preparation_time": 0.0023,
24
+ "eval_runtime": 481.4814,
25
+ "eval_samples_per_second": 55.003,
26
+ "eval_steps_per_second": 6.877,
27
+ "step": 828
28
+ },
29
+ {
30
+ "epoch": 1.2077294685990339,
31
+ "grad_norm": 4.54465913772583,
32
+ "learning_rate": 0.00012193919474116682,
33
+ "loss": 0.8238,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 1.8115942028985508,
38
+ "grad_norm": 9.120803833007812,
39
+ "learning_rate": 8.08545603944125e-05,
40
+ "loss": 0.71,
41
+ "step": 1500
42
+ },
43
+ {
44
+ "epoch": 2.0,
45
+ "eval_accuracy": 0.785258467696258,
46
+ "eval_loss": 0.5553735494613647,
47
+ "eval_model_preparation_time": 0.0023,
48
+ "eval_runtime": 482.7837,
49
+ "eval_samples_per_second": 54.855,
50
+ "eval_steps_per_second": 6.858,
51
+ "step": 1656
52
+ },
53
+ {
54
+ "epoch": 2.4154589371980677,
55
+ "grad_norm": 5.409132957458496,
56
+ "learning_rate": 3.976992604765818e-05,
57
+ "loss": 0.5791,
58
+ "step": 2000
59
+ },
60
+ {
61
+ "epoch": 3.0,
62
+ "eval_accuracy": 0.8295510327379828,
63
+ "eval_loss": 0.43748077750205994,
64
+ "eval_model_preparation_time": 0.0023,
65
+ "eval_runtime": 481.8468,
66
+ "eval_samples_per_second": 54.961,
67
+ "eval_steps_per_second": 6.871,
68
+ "step": 2484
69
+ }
70
+ ],
71
+ "logging_steps": 500,
72
+ "max_steps": 2484,
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": 6.654455928125172e+18,
89
+ "train_batch_size": 32,
90
+ "trial_name": null,
91
+ "trial_params": null
92
+ }
checkpoint-2484/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77f0ca87b3994c04b4f018469a0d2842d64d1c9897f79e494161c2d4afdb6510
3
+ size 5304
checkpoint-828/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Anime Picture",
7
+ "1": "Hentai",
8
+ "2": "Neutral",
9
+ "3": "Pornography",
10
+ "4": "Enticing or Sensual"
11
+ },
12
+ "initializer_factor": 1.0,
13
+ "label2id": {
14
+ "Anime Picture": 0,
15
+ "Enticing or Sensual": 4,
16
+ "Hentai": 1,
17
+ "Neutral": 2,
18
+ "Pornography": 3
19
+ },
20
+ "model_type": "siglip",
21
+ "problem_type": "single_label_classification",
22
+ "text_config": {
23
+ "attention_dropout": 0.0,
24
+ "hidden_act": "gelu_pytorch_tanh",
25
+ "hidden_size": 768,
26
+ "intermediate_size": 3072,
27
+ "layer_norm_eps": 1e-06,
28
+ "max_position_embeddings": 64,
29
+ "model_type": "siglip_text_model",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "projection_size": 768,
33
+ "torch_dtype": "float32",
34
+ "vocab_size": 256000
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.50.3",
38
+ "vision_config": {
39
+ "attention_dropout": 0.0,
40
+ "hidden_act": "gelu_pytorch_tanh",
41
+ "hidden_size": 768,
42
+ "image_size": 224,
43
+ "intermediate_size": 3072,
44
+ "layer_norm_eps": 1e-06,
45
+ "model_type": "siglip_vision_model",
46
+ "num_attention_heads": 12,
47
+ "num_channels": 3,
48
+ "num_hidden_layers": 12,
49
+ "patch_size": 16,
50
+ "torch_dtype": "float32"
51
+ }
52
+ }
checkpoint-828/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715738b8be6a085d2b43e398280cd8d2d8c391f35b8507f9ab45a437b5b66a54
3
+ size 371577220
checkpoint-828/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf0ab4127239e064190c0d789959e15241102aa9201eb6251978b4fcfe94c63d
3
+ size 686574202
checkpoint-828/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-828/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ef17702a0725d2ce6b58c8dbb73765893aabc8ef91b4de533167fc5ea45b4b6
3
+ size 14244
checkpoint-828/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:317a7aa06c6e669f9e2dcd3ffc6ff2b053874bb84dbf7a55f9477d2d7ca80f1d
3
+ size 1064
checkpoint-828/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 828,
3
+ "best_metric": 0.7443631291389465,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-828",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 828,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.6038647342995169,
14
+ "grad_norm": 3.9172444343566895,
15
+ "learning_rate": 0.00016302382908792113,
16
+ "loss": 1.1039,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.7029792697201979,
22
+ "eval_loss": 0.7443631291389465,
23
+ "eval_model_preparation_time": 0.0023,
24
+ "eval_runtime": 481.4814,
25
+ "eval_samples_per_second": 55.003,
26
+ "eval_steps_per_second": 6.877,
27
+ "step": 828
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 2484,
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": 2.218151976041724e+18,
48
+ "train_batch_size": 32,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
checkpoint-828/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77f0ca87b3994c04b4f018469a0d2842d64d1c9897f79e494161c2d4afdb6510
3
+ size 5304
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Anime Picture",
7
+ "1": "Hentai",
8
+ "2": "Neutral",
9
+ "3": "Pornography",
10
+ "4": "Enticing or Sensual"
11
+ },
12
+ "initializer_factor": 1.0,
13
+ "label2id": {
14
+ "Anime Picture": 0,
15
+ "Enticing or Sensual": 4,
16
+ "Hentai": 1,
17
+ "Neutral": 2,
18
+ "Pornography": 3
19
+ },
20
+ "model_type": "siglip",
21
+ "problem_type": "single_label_classification",
22
+ "text_config": {
23
+ "attention_dropout": 0.0,
24
+ "hidden_act": "gelu_pytorch_tanh",
25
+ "hidden_size": 768,
26
+ "intermediate_size": 3072,
27
+ "layer_norm_eps": 1e-06,
28
+ "max_position_embeddings": 64,
29
+ "model_type": "siglip_text_model",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "projection_size": 768,
33
+ "torch_dtype": "float32",
34
+ "vocab_size": 256000
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.50.3",
38
+ "vision_config": {
39
+ "attention_dropout": 0.0,
40
+ "hidden_act": "gelu_pytorch_tanh",
41
+ "hidden_size": 768,
42
+ "image_size": 224,
43
+ "intermediate_size": 3072,
44
+ "layer_norm_eps": 1e-06,
45
+ "model_type": "siglip_vision_model",
46
+ "num_attention_heads": 12,
47
+ "num_channels": 3,
48
+ "num_hidden_layers": 12,
49
+ "patch_size": 16,
50
+ "torch_dtype": "float32"
51
+ }
52
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b56c9793be0162dfaf7662ab6ef9fc38c03a3533880a8ed98b3039c203a3865
3
+ size 371577220
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 sha256:77f0ca87b3994c04b4f018469a0d2842d64d1c9897f79e494161c2d4afdb6510
3
+ size 5304