Hugging Face's logo

prithivMLmods
/
Emoji-Scope

Image Classification
Transformers
Safetensors
English
siglip
Emoji-Scope
Google
CrossEmoji Classifier
Model card Files Community
prithivMLmods commited on
Commit
6352ca0
·
verified ·
1 Parent(s): 992778e

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. checkpoint-268/config.json +64 -0
  2. checkpoint-268/model.safetensors +3 -0
  3. checkpoint-268/optimizer.pt +3 -0
  4. checkpoint-268/preprocessor_config.json +24 -0
  5. checkpoint-268/rng_state.pth +3 -0
  6. checkpoint-268/scheduler.pt +3 -0
  7. checkpoint-268/trainer_state.json +44 -0
  8. checkpoint-268/training_args.bin +3 -0
  9. checkpoint-536/config.json +64 -0
  10. checkpoint-536/model.safetensors +3 -0
  11. checkpoint-536/optimizer.pt +3 -0
  12. checkpoint-536/preprocessor_config.json +24 -0
  13. checkpoint-536/rng_state.pth +3 -0
  14. checkpoint-536/scheduler.pt +3 -0
  15. checkpoint-536/trainer_state.json +61 -0
  16. checkpoint-536/training_args.bin +3 -0
  17. checkpoint-804/config.json +64 -0
  18. checkpoint-804/model.safetensors +3 -0
  19. checkpoint-804/optimizer.pt +3 -0
  20. checkpoint-804/preprocessor_config.json +24 -0
  21. checkpoint-804/rng_state.pth +3 -0
  22. checkpoint-804/scheduler.pt +3 -0
  23. checkpoint-804/trainer_state.json +71 -0
  24. checkpoint-804/training_args.bin +3 -0
  25. config.json +64 -0
  26. model.safetensors +3 -0
  27. preprocessor_config.json +24 -0
  28. training_args.bin +3 -0
checkpoint-268/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Apple Style",
7
+ "1": "DoCoMo Style",
8
+ "2": "Facebook Style",
9
+ "3": "Gmail Style",
10
+ "4": "Google Style",
11
+ "5": "JoyPixels Style",
12
+ "6": "KDDI Style",
13
+ "7": "Samsung Style",
14
+ "8": "SoftBank Style",
15
+ "9": "Twitter Style",
16
+ "10": "Windows Style"
17
+ },
18
+ "initializer_factor": 1.0,
19
+ "label2id": {
20
+ "Apple Style": 0,
21
+ "DoCoMo Style": 1,
22
+ "Facebook Style": 2,
23
+ "Gmail Style": 3,
24
+ "Google Style": 4,
25
+ "JoyPixels Style": 5,
26
+ "KDDI Style": 6,
27
+ "Samsung Style": 7,
28
+ "SoftBank Style": 8,
29
+ "Twitter Style": 9,
30
+ "Windows Style": 10
31
+ },
32
+ "model_type": "siglip",
33
+ "problem_type": "single_label_classification",
34
+ "text_config": {
35
+ "attention_dropout": 0.0,
36
+ "hidden_act": "gelu_pytorch_tanh",
37
+ "hidden_size": 768,
38
+ "intermediate_size": 3072,
39
+ "layer_norm_eps": 1e-06,
40
+ "max_position_embeddings": 64,
41
+ "model_type": "siglip_text_model",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 12,
44
+ "projection_size": 768,
45
+ "torch_dtype": "float32",
46
+ "vocab_size": 256000
47
+ },
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.50.2",
50
+ "vision_config": {
51
+ "attention_dropout": 0.0,
52
+ "hidden_act": "gelu_pytorch_tanh",
53
+ "hidden_size": 768,
54
+ "image_size": 224,
55
+ "intermediate_size": 3072,
56
+ "layer_norm_eps": 1e-06,
57
+ "model_type": "siglip_vision_model",
58
+ "num_attention_heads": 12,
59
+ "num_channels": 3,
60
+ "num_hidden_layers": 12,
61
+ "patch_size": 16,
62
+ "torch_dtype": "float32"
63
+ }
64
+ }
checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a409233e8a1d37c2e6025a5822ceadc42d0e7b7870e20ffb3a968d5aedf3c94
3
+ size 371595684
checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a56c4c545fd93e857b77d577a5680d08d3d8ec201b7aedd90ca87067696bb7
3
+ size 686611066
checkpoint-268/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-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:decf0c6956d2a5c4c814e3dea800ace8aebf45e43e0d342844524ba391969493
3
+ size 14244
checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:131394b78dbd39b7cbce59d83683a280c868dc77923a8fadb04062ca6a16b9bd
3
+ size 1064
checkpoint-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 268,
3
+ "best_metric": 0.6867316961288452,
4
+ "best_model_checkpoint": "siglip2-finetune/checkpoint-268",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 268,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.7478077867414942,
15
+ "eval_loss": 0.6867316961288452,
16
+ "eval_model_preparation_time": 0.0039,
17
+ "eval_runtime": 73.0639,
18
+ "eval_samples_per_second": 78.041,
19
+ "eval_steps_per_second": 9.759,
20
+ "step": 268
21
+ }
22
+ ],
23
+ "logging_steps": 500,
24
+ "max_steps": 804,
25
+ "num_input_tokens_seen": 0,
26
+ "num_train_epochs": 3,
27
+ "save_steps": 500,
28
+ "stateful_callbacks": {
29
+ "TrainerControl": {
30
+ "args": {
31
+ "should_epoch_stop": false,
32
+ "should_evaluate": false,
33
+ "should_log": false,
34
+ "should_save": true,
35
+ "should_training_stop": false
36
+ },
37
+ "attributes": {}
38
+ }
39
+ },
40
+ "total_flos": 7.16246695578839e+17,
41
+ "train_batch_size": 32,
42
+ "trial_name": null,
43
+ "trial_params": null
44
+ }
checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b8ef3681b5c37988acd09f9737a867985bc926b743a436b6231d47d250f51f1
3
+ size 5304
checkpoint-536/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Apple Style",
7
+ "1": "DoCoMo Style",
8
+ "2": "Facebook Style",
9
+ "3": "Gmail Style",
10
+ "4": "Google Style",
11
+ "5": "JoyPixels Style",
12
+ "6": "KDDI Style",
13
+ "7": "Samsung Style",
14
+ "8": "SoftBank Style",
15
+ "9": "Twitter Style",
16
+ "10": "Windows Style"
17
+ },
18
+ "initializer_factor": 1.0,
19
+ "label2id": {
20
+ "Apple Style": 0,
21
+ "DoCoMo Style": 1,
22
+ "Facebook Style": 2,
23
+ "Gmail Style": 3,
24
+ "Google Style": 4,
25
+ "JoyPixels Style": 5,
26
+ "KDDI Style": 6,
27
+ "Samsung Style": 7,
28
+ "SoftBank Style": 8,
29
+ "Twitter Style": 9,
30
+ "Windows Style": 10
31
+ },
32
+ "model_type": "siglip",
33
+ "problem_type": "single_label_classification",
34
+ "text_config": {
35
+ "attention_dropout": 0.0,
36
+ "hidden_act": "gelu_pytorch_tanh",
37
+ "hidden_size": 768,
38
+ "intermediate_size": 3072,
39
+ "layer_norm_eps": 1e-06,
40
+ "max_position_embeddings": 64,
41
+ "model_type": "siglip_text_model",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 12,
44
+ "projection_size": 768,
45
+ "torch_dtype": "float32",
46
+ "vocab_size": 256000
47
+ },
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.50.2",
50
+ "vision_config": {
51
+ "attention_dropout": 0.0,
52
+ "hidden_act": "gelu_pytorch_tanh",
53
+ "hidden_size": 768,
54
+ "image_size": 224,
55
+ "intermediate_size": 3072,
56
+ "layer_norm_eps": 1e-06,
57
+ "model_type": "siglip_vision_model",
58
+ "num_attention_heads": 12,
59
+ "num_channels": 3,
60
+ "num_hidden_layers": 12,
61
+ "patch_size": 16,
62
+ "torch_dtype": "float32"
63
+ }
64
+ }
checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d5f0da88ebccb954fb26f3e9df058a5073c1a1e1d8cc4d5f42046112198ca3
3
+ size 371595684
checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25305be08af26217e1fab7f7528810d59c4cfcc3c3791df262b84331e6aaf247
3
+ size 686611066
checkpoint-536/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-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b11780efaf71545432a80a491752144598485357051b46fe6d9163abd18d0a2c
3
+ size 14244
checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5d2bac5f44ca12d5cd9db4d776f584288f9edf2f2a1a4e1c5b6a4b5b885f9ee
3
+ size 1064
checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 536,
3
+ "best_metric": 0.3235144019126892,
4
+ "best_model_checkpoint": "siglip2-finetune/checkpoint-536",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 536,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.7478077867414942,
15
+ "eval_loss": 0.6867316961288452,
16
+ "eval_model_preparation_time": 0.0039,
17
+ "eval_runtime": 73.0639,
18
+ "eval_samples_per_second": 78.041,
19
+ "eval_steps_per_second": 9.759,
20
+ "step": 268
21
+ },
22
+ {
23
+ "epoch": 1.8656716417910446,
24
+ "grad_norm": 11.605195045471191,
25
+ "learning_rate": 4.031830238726791e-05,
26
+ "loss": 0.6005,
27
+ "step": 500
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "eval_accuracy": 0.8921431076815153,
32
+ "eval_loss": 0.3235144019126892,
33
+ "eval_model_preparation_time": 0.0039,
34
+ "eval_runtime": 72.6895,
35
+ "eval_samples_per_second": 78.443,
36
+ "eval_steps_per_second": 9.809,
37
+ "step": 536
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 804,
42
+ "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 3,
44
+ "save_steps": 500,
45
+ "stateful_callbacks": {
46
+ "TrainerControl": {
47
+ "args": {
48
+ "should_epoch_stop": false,
49
+ "should_evaluate": false,
50
+ "should_log": false,
51
+ "should_save": true,
52
+ "should_training_stop": false
53
+ },
54
+ "attributes": {}
55
+ }
56
+ },
57
+ "total_flos": 1.432493391157678e+18,
58
+ "train_batch_size": 32,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b8ef3681b5c37988acd09f9737a867985bc926b743a436b6231d47d250f51f1
3
+ size 5304
checkpoint-804/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Apple Style",
7
+ "1": "DoCoMo Style",
8
+ "2": "Facebook Style",
9
+ "3": "Gmail Style",
10
+ "4": "Google Style",
11
+ "5": "JoyPixels Style",
12
+ "6": "KDDI Style",
13
+ "7": "Samsung Style",
14
+ "8": "SoftBank Style",
15
+ "9": "Twitter Style",
16
+ "10": "Windows Style"
17
+ },
18
+ "initializer_factor": 1.0,
19
+ "label2id": {
20
+ "Apple Style": 0,
21
+ "DoCoMo Style": 1,
22
+ "Facebook Style": 2,
23
+ "Gmail Style": 3,
24
+ "Google Style": 4,
25
+ "JoyPixels Style": 5,
26
+ "KDDI Style": 6,
27
+ "Samsung Style": 7,
28
+ "SoftBank Style": 8,
29
+ "Twitter Style": 9,
30
+ "Windows Style": 10
31
+ },
32
+ "model_type": "siglip",
33
+ "problem_type": "single_label_classification",
34
+ "text_config": {
35
+ "attention_dropout": 0.0,
36
+ "hidden_act": "gelu_pytorch_tanh",
37
+ "hidden_size": 768,
38
+ "intermediate_size": 3072,
39
+ "layer_norm_eps": 1e-06,
40
+ "max_position_embeddings": 64,
41
+ "model_type": "siglip_text_model",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 12,
44
+ "projection_size": 768,
45
+ "torch_dtype": "float32",
46
+ "vocab_size": 256000
47
+ },
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.50.2",
50
+ "vision_config": {
51
+ "attention_dropout": 0.0,
52
+ "hidden_act": "gelu_pytorch_tanh",
53
+ "hidden_size": 768,
54
+ "image_size": 224,
55
+ "intermediate_size": 3072,
56
+ "layer_norm_eps": 1e-06,
57
+ "model_type": "siglip_vision_model",
58
+ "num_attention_heads": 12,
59
+ "num_channels": 3,
60
+ "num_hidden_layers": 12,
61
+ "patch_size": 16,
62
+ "torch_dtype": "float32"
63
+ }
64
+ }
checkpoint-804/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4acc15f80b59cdeb1cca82f7df00581e672d8c2472147ad5776ec856aa9f58c4
3
+ size 371595684
checkpoint-804/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bbca1da75dcd894d02769993215514eaa74aafa2fe7bc0ff7e91ac98cd0cb43
3
+ size 686611066
checkpoint-804/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-804/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b729e849b2d42ea4a0fadcf3c443c92694e4363e752f7f4573447a8cf2ae052
3
+ size 14244
checkpoint-804/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a10bbe61232e39d362528c52a317451e511130d35801a979c8521fbaaa0bfe
3
+ size 1064
checkpoint-804/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 804,
3
+ "best_metric": 0.23307399451732635,
4
+ "best_model_checkpoint": "siglip2-finetune/checkpoint-804",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 804,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.7478077867414942,
15
+ "eval_loss": 0.6867316961288452,
16
+ "eval_model_preparation_time": 0.0039,
17
+ "eval_runtime": 73.0639,
18
+ "eval_samples_per_second": 78.041,
19
+ "eval_steps_per_second": 9.759,
20
+ "step": 268
21
+ },
22
+ {
23
+ "epoch": 1.8656716417910446,
24
+ "grad_norm": 11.605195045471191,
25
+ "learning_rate": 4.031830238726791e-05,
26
+ "loss": 0.6005,
27
+ "step": 500
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "eval_accuracy": 0.8921431076815153,
32
+ "eval_loss": 0.3235144019126892,
33
+ "eval_model_preparation_time": 0.0039,
34
+ "eval_runtime": 72.6895,
35
+ "eval_samples_per_second": 78.443,
36
+ "eval_steps_per_second": 9.809,
37
+ "step": 536
38
+ },
39
+ {
40
+ "epoch": 3.0,
41
+ "eval_accuracy": 0.9200280603297089,
42
+ "eval_loss": 0.23307399451732635,
43
+ "eval_model_preparation_time": 0.0039,
44
+ "eval_runtime": 72.6624,
45
+ "eval_samples_per_second": 78.473,
46
+ "eval_steps_per_second": 9.813,
47
+ "step": 804
48
+ }
49
+ ],
50
+ "logging_steps": 500,
51
+ "max_steps": 804,
52
+ "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 3,
54
+ "save_steps": 500,
55
+ "stateful_callbacks": {
56
+ "TrainerControl": {
57
+ "args": {
58
+ "should_epoch_stop": false,
59
+ "should_evaluate": false,
60
+ "should_log": false,
61
+ "should_save": true,
62
+ "should_training_stop": true
63
+ },
64
+ "attributes": {}
65
+ }
66
+ },
67
+ "total_flos": 2.148740086736517e+18,
68
+ "train_batch_size": 32,
69
+ "trial_name": null,
70
+ "trial_params": null
71
+ }
checkpoint-804/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b8ef3681b5c37988acd09f9737a867985bc926b743a436b6231d47d250f51f1
3
+ size 5304
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "Apple Style",
7
+ "1": "DoCoMo Style",
8
+ "2": "Facebook Style",
9
+ "3": "Gmail Style",
10
+ "4": "Google Style",
11
+ "5": "JoyPixels Style",
12
+ "6": "KDDI Style",
13
+ "7": "Samsung Style",
14
+ "8": "SoftBank Style",
15
+ "9": "Twitter Style",
16
+ "10": "Windows Style"
17
+ },
18
+ "initializer_factor": 1.0,
19
+ "label2id": {
20
+ "Apple Style": 0,
21
+ "DoCoMo Style": 1,
22
+ "Facebook Style": 2,
23
+ "Gmail Style": 3,
24
+ "Google Style": 4,
25
+ "JoyPixels Style": 5,
26
+ "KDDI Style": 6,
27
+ "Samsung Style": 7,
28
+ "SoftBank Style": 8,
29
+ "Twitter Style": 9,
30
+ "Windows Style": 10
31
+ },
32
+ "model_type": "siglip",
33
+ "problem_type": "single_label_classification",
34
+ "text_config": {
35
+ "attention_dropout": 0.0,
36
+ "hidden_act": "gelu_pytorch_tanh",
37
+ "hidden_size": 768,
38
+ "intermediate_size": 3072,
39
+ "layer_norm_eps": 1e-06,
40
+ "max_position_embeddings": 64,
41
+ "model_type": "siglip_text_model",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 12,
44
+ "projection_size": 768,
45
+ "torch_dtype": "float32",
46
+ "vocab_size": 256000
47
+ },
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.50.2",
50
+ "vision_config": {
51
+ "attention_dropout": 0.0,
52
+ "hidden_act": "gelu_pytorch_tanh",
53
+ "hidden_size": 768,
54
+ "image_size": 224,
55
+ "intermediate_size": 3072,
56
+ "layer_norm_eps": 1e-06,
57
+ "model_type": "siglip_vision_model",
58
+ "num_attention_heads": 12,
59
+ "num_channels": 3,
60
+ "num_hidden_layers": 12,
61
+ "patch_size": 16,
62
+ "torch_dtype": "float32"
63
+ }
64
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4acc15f80b59cdeb1cca82f7df00581e672d8c2472147ad5776ec856aa9f58c4
3
+ size 371595684
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 sha256:6b8ef3681b5c37988acd09f9737a867985bc926b743a436b6231d47d250f51f1
3
+ size 5304