prithivMLmods commited on
Commit
a592270
·
verified ·
1 Parent(s): 1430bd9

Upload folder using huggingface_hub

Browse files
checkpoint-1190/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Child 0-12",
7
+ "1": "Teenager 13-20",
8
+ "2": "Adult 21-44",
9
+ "3": "Middle Age 45-64",
10
+ "4": "Aged 65+"
11
+ },
12
+ "initializer_factor": 1.0,
13
+ "label2id": {
14
+ "Adult 21-44": 2,
15
+ "Aged 65+": 4,
16
+ "Child 0-12": 0,
17
+ "Middle Age 45-64": 3,
18
+ "Teenager 13-20": 1
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": "4.50.0",
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-1190/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e51c7a5eb7f8086a0d7648df3532d0ef9c122891c7c90c8d82f0f106f1b0630e
3
+ size 371577220
checkpoint-1190/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4be954cb1a61d8d73d27821495c5074332bdf36ce73b2f31eab3f20ce284b4b6
3
+ size 686574202
checkpoint-1190/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-1190/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2b8bb857b275788df3a4bfe6c58412c20f635cf16b03ce1fb0bccf24f56310b
3
+ size 14244
checkpoint-1190/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:415f080bbdfdd30f9b12b864ba008fa84d3d4888c59f3e20fa3e134dd8668394
3
+ size 1064
checkpoint-1190/trainer_state.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1190,
3
+ "best_metric": 0.2564544677734375,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1190",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1190,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.8403361344537815,
14
+ "grad_norm": 21.780553817749023,
15
+ "learning_rate": 1.4812680115273776e-05,
16
+ "loss": 0.7499,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8325094657130837,
22
+ "eval_loss": 0.4362837076187134,
23
+ "eval_model_preparation_time": 0.0022,
24
+ "eval_runtime": 307.2598,
25
+ "eval_samples_per_second": 61.889,
26
+ "eval_steps_per_second": 7.736,
27
+ "step": 595
28
+ },
29
+ {
30
+ "epoch": 1.680672268907563,
31
+ "grad_norm": 19.866661071777344,
32
+ "learning_rate": 9.048991354466859e-06,
33
+ "loss": 0.4428,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.9009255363904081,
39
+ "eval_loss": 0.2564544677734375,
40
+ "eval_model_preparation_time": 0.0022,
41
+ "eval_runtime": 304.8059,
42
+ "eval_samples_per_second": 62.387,
43
+ "eval_steps_per_second": 7.798,
44
+ "step": 1190
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 1785,
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": 3.1854682608775004e+18,
65
+ "train_batch_size": 32,
66
+ "trial_name": null,
67
+ "trial_params": null
68
+ }
checkpoint-1190/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934b156616eb42b0372213043039ea9bbb8119e6566468a293ca4bdd27d98d7a
3
+ size 5304
checkpoint-1785/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Child 0-12",
7
+ "1": "Teenager 13-20",
8
+ "2": "Adult 21-44",
9
+ "3": "Middle Age 45-64",
10
+ "4": "Aged 65+"
11
+ },
12
+ "initializer_factor": 1.0,
13
+ "label2id": {
14
+ "Adult 21-44": 2,
15
+ "Aged 65+": 4,
16
+ "Child 0-12": 0,
17
+ "Middle Age 45-64": 3,
18
+ "Teenager 13-20": 1
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": "4.50.0",
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-1785/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9496500de8132e5557aa7849756e59a5aa4b7f28495dc3e2b98a70bf697eced9
3
+ size 371577220
checkpoint-1785/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e9ee8a4c7ca6df517790481cbe6a99a4f7b8011189607e94db5dee3fb18815b
3
+ size 686574202
checkpoint-1785/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-1785/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35bad94d3860ee97520c76c204fc73a3a0ea97862ce78616f228143e0990d2e0
3
+ size 14244
checkpoint-1785/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ef96fc78d875e360bc44631ecd2069625c7b807413ab6eaf861425c0750b8a0
3
+ size 1064
checkpoint-1785/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1785,
3
+ "best_metric": 0.09230011701583862,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-1785",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1785,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.8403361344537815,
14
+ "grad_norm": 21.780553817749023,
15
+ "learning_rate": 1.4812680115273776e-05,
16
+ "loss": 0.7499,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8325094657130837,
22
+ "eval_loss": 0.4362837076187134,
23
+ "eval_model_preparation_time": 0.0022,
24
+ "eval_runtime": 307.2598,
25
+ "eval_samples_per_second": 61.889,
26
+ "eval_steps_per_second": 7.736,
27
+ "step": 595
28
+ },
29
+ {
30
+ "epoch": 1.680672268907563,
31
+ "grad_norm": 19.866661071777344,
32
+ "learning_rate": 9.048991354466859e-06,
33
+ "loss": 0.4428,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.9009255363904081,
39
+ "eval_loss": 0.2564544677734375,
40
+ "eval_model_preparation_time": 0.0022,
41
+ "eval_runtime": 304.8059,
42
+ "eval_samples_per_second": 62.387,
43
+ "eval_steps_per_second": 7.798,
44
+ "step": 1190
45
+ },
46
+ {
47
+ "epoch": 2.5210084033613445,
48
+ "grad_norm": 10.98959732055664,
49
+ "learning_rate": 3.2853025936599425e-06,
50
+ "loss": 0.2399,
51
+ "step": 1500
52
+ },
53
+ {
54
+ "epoch": 3.0,
55
+ "eval_accuracy": 0.9690786705931846,
56
+ "eval_loss": 0.09230011701583862,
57
+ "eval_model_preparation_time": 0.0022,
58
+ "eval_runtime": 307.0858,
59
+ "eval_samples_per_second": 61.924,
60
+ "eval_steps_per_second": 7.741,
61
+ "step": 1785
62
+ }
63
+ ],
64
+ "logging_steps": 500,
65
+ "max_steps": 1785,
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": 4.778202391316251e+18,
82
+ "train_batch_size": 32,
83
+ "trial_name": null,
84
+ "trial_params": null
85
+ }
checkpoint-1785/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934b156616eb42b0372213043039ea9bbb8119e6566468a293ca4bdd27d98d7a
3
+ size 5304
checkpoint-595/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Child 0-12",
7
+ "1": "Teenager 13-20",
8
+ "2": "Adult 21-44",
9
+ "3": "Middle Age 45-64",
10
+ "4": "Aged 65+"
11
+ },
12
+ "initializer_factor": 1.0,
13
+ "label2id": {
14
+ "Adult 21-44": 2,
15
+ "Aged 65+": 4,
16
+ "Child 0-12": 0,
17
+ "Middle Age 45-64": 3,
18
+ "Teenager 13-20": 1
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": "4.50.0",
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-595/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:207e6b2e5954bea4ea27a784b88dec1ce703d480642beb5dee9a9f2096086bcc
3
+ size 371577220
checkpoint-595/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9e1dff26cde2e4232667782cedbc2a45949891a243aa15226141270a45d6fa9
3
+ size 686574202
checkpoint-595/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-595/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5181ecb6c4a34a3fa80f328ab2cae756bf09870289fe50718f33f41161538f4d
3
+ size 14244
checkpoint-595/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f583ae98a8698c30bfbbd2bde425267a668853b3bccc16d032520905f30ac138
3
+ size 1064
checkpoint-595/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 595,
3
+ "best_metric": 0.4362837076187134,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-595",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 595,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.8403361344537815,
14
+ "grad_norm": 21.780553817749023,
15
+ "learning_rate": 1.4812680115273776e-05,
16
+ "loss": 0.7499,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8325094657130837,
22
+ "eval_loss": 0.4362837076187134,
23
+ "eval_model_preparation_time": 0.0022,
24
+ "eval_runtime": 307.2598,
25
+ "eval_samples_per_second": 61.889,
26
+ "eval_steps_per_second": 7.736,
27
+ "step": 595
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 1785,
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": 1.5927341304387502e+18,
48
+ "train_batch_size": 32,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
checkpoint-595/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934b156616eb42b0372213043039ea9bbb8119e6566468a293ca4bdd27d98d7a
3
+ size 5304
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Child 0-12",
7
+ "1": "Teenager 13-20",
8
+ "2": "Adult 21-44",
9
+ "3": "Middle Age 45-64",
10
+ "4": "Aged 65+"
11
+ },
12
+ "initializer_factor": 1.0,
13
+ "label2id": {
14
+ "Adult 21-44": 2,
15
+ "Aged 65+": 4,
16
+ "Child 0-12": 0,
17
+ "Middle Age 45-64": 3,
18
+ "Teenager 13-20": 1
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": "4.50.0",
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 sha256:9496500de8132e5557aa7849756e59a5aa4b7f28495dc3e2b98a70bf697eced9
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 sha256:934b156616eb42b0372213043039ea9bbb8119e6566468a293ca4bdd27d98d7a
3
+ size 5304