Hugging Face's logo

prithivMLmods
/
MetaCLIP-2-Gender-Identifier

Image Classification
Transformers
Safetensors
English
metaclip_2
text-generation-inference
gender-identifier
Model card Files
xet
Community
prithivMLmods commited on
Commit
a8dd724
·
verified ·
1 Parent(s): 7ebb835

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. checkpoint-100/config.json +54 -0
  2. checkpoint-100/model.safetensors +3 -0
  3. checkpoint-100/optimizer.pt +3 -0
  4. checkpoint-100/preprocessor_config.json +29 -0
  5. checkpoint-100/rng_state.pth +3 -0
  6. checkpoint-100/scheduler.pt +3 -0
  7. checkpoint-100/trainer_state.json +44 -0
  8. checkpoint-100/training_args.bin +3 -0
  9. checkpoint-200/config.json +54 -0
  10. checkpoint-200/model.safetensors +3 -0
  11. checkpoint-200/optimizer.pt +3 -0
  12. checkpoint-200/preprocessor_config.json +29 -0
  13. checkpoint-200/rng_state.pth +3 -0
  14. checkpoint-200/scheduler.pt +3 -0
  15. checkpoint-200/trainer_state.json +54 -0
  16. checkpoint-200/training_args.bin +3 -0
  17. checkpoint-300/config.json +54 -0
  18. checkpoint-300/model.safetensors +3 -0
  19. checkpoint-300/optimizer.pt +3 -0
  20. checkpoint-300/preprocessor_config.json +29 -0
  21. checkpoint-300/rng_state.pth +3 -0
  22. checkpoint-300/scheduler.pt +3 -0
  23. checkpoint-300/trainer_state.json +64 -0
  24. checkpoint-300/training_args.bin +3 -0
  25. config.json +54 -0
  26. model.safetensors +3 -0
  27. preprocessor_config.json +29 -0
  28. training_args.bin +3 -0
checkpoint-100/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MetaClip2ForImageClassification"
4
+ ],
5
+ "dtype": "float32",
6
+ "id2label": {
7
+ "0": "female",
8
+ "1": "male"
9
+ },
10
+ "initializer_factor": 1.0,
11
+ "label2id": {
12
+ "female": 0,
13
+ "male": 1
14
+ },
15
+ "logit_scale_init_value": 2.6592,
16
+ "model_type": "metaclip_2",
17
+ "problem_type": "single_label_classification",
18
+ "projection_dim": 384,
19
+ "text_config": {
20
+ "attention_dropout": 0.0,
21
+ "dtype": "float32",
22
+ "eos_token_id": 2,
23
+ "hidden_act": "gelu",
24
+ "hidden_size": 384,
25
+ "initializer_factor": 1.0,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 1536,
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 77,
30
+ "model_type": "metaclip_2_text_model",
31
+ "num_attention_heads": 6,
32
+ "num_hidden_layers": 12,
33
+ "projection_dim": 384,
34
+ "vocab_size": 901629
35
+ },
36
+ "transformers_version": "4.57.1",
37
+ "vision_config": {
38
+ "attention_dropout": 0.0,
39
+ "dtype": "float32",
40
+ "hidden_act": "gelu",
41
+ "hidden_size": 384,
42
+ "image_size": 224,
43
+ "initializer_factor": 1.0,
44
+ "initializer_range": 0.02,
45
+ "intermediate_size": 1536,
46
+ "layer_norm_eps": 1e-05,
47
+ "model_type": "metaclip_2_vision_model",
48
+ "num_attention_heads": 6,
49
+ "num_channels": 3,
50
+ "num_hidden_layers": 12,
51
+ "patch_size": 16,
52
+ "projection_dim": 384
53
+ }
54
+ }
checkpoint-100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ac1fae09a4c42f30be505d35af48913792f024955cd9eb96e33c5d7e38392a
3
+ size 86690920
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a44c76a5072ab6a087abee79116dec6083d80550e769fe3f7e7e0febd85654
3
+ size 173498123
checkpoint-100/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "processor_class": "CLIPProcessor",
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 224,
27
+ "width": 224
28
+ }
29
+ }
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7fc6614bae48724a00923b6dac5897177b9f8e0b21d015e919472d5625037ef
3
+ size 14645
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5682e217f7b0fcc87faea418492455ffabdd8b4f20160b24f9eb08f6ff256c2c
3
+ size 1465
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 100,
3
+ "best_metric": 0.11963150650262833,
4
+ "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-100",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 100,
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": 0.94625,
15
+ "eval_loss": 0.11963150650262833,
16
+ "eval_model_preparation_time": 0.003,
17
+ "eval_runtime": 169.7911,
18
+ "eval_samples_per_second": 18.847,
19
+ "eval_steps_per_second": 2.356,
20
+ "step": 100
21
+ }
22
+ ],
23
+ "logging_steps": 500,
24
+ "max_steps": 300,
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": 6.2401452244992e+16,
41
+ "train_batch_size": 32,
42
+ "trial_name": null,
43
+ "trial_params": null
44
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6072cf5c917b1b93ccbdb1b8bb5ab626fca6efc4913a5ad3ed0b4a994467d8d3
3
+ size 5777
checkpoint-200/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MetaClip2ForImageClassification"
4
+ ],
5
+ "dtype": "float32",
6
+ "id2label": {
7
+ "0": "female",
8
+ "1": "male"
9
+ },
10
+ "initializer_factor": 1.0,
11
+ "label2id": {
12
+ "female": 0,
13
+ "male": 1
14
+ },
15
+ "logit_scale_init_value": 2.6592,
16
+ "model_type": "metaclip_2",
17
+ "problem_type": "single_label_classification",
18
+ "projection_dim": 384,
19
+ "text_config": {
20
+ "attention_dropout": 0.0,
21
+ "dtype": "float32",
22
+ "eos_token_id": 2,
23
+ "hidden_act": "gelu",
24
+ "hidden_size": 384,
25
+ "initializer_factor": 1.0,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 1536,
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 77,
30
+ "model_type": "metaclip_2_text_model",
31
+ "num_attention_heads": 6,
32
+ "num_hidden_layers": 12,
33
+ "projection_dim": 384,
34
+ "vocab_size": 901629
35
+ },
36
+ "transformers_version": "4.57.1",
37
+ "vision_config": {
38
+ "attention_dropout": 0.0,
39
+ "dtype": "float32",
40
+ "hidden_act": "gelu",
41
+ "hidden_size": 384,
42
+ "image_size": 224,
43
+ "initializer_factor": 1.0,
44
+ "initializer_range": 0.02,
45
+ "intermediate_size": 1536,
46
+ "layer_norm_eps": 1e-05,
47
+ "model_type": "metaclip_2_vision_model",
48
+ "num_attention_heads": 6,
49
+ "num_channels": 3,
50
+ "num_hidden_layers": 12,
51
+ "patch_size": 16,
52
+ "projection_dim": 384
53
+ }
54
+ }
checkpoint-200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082e4280922df758022a393d7a436a97831502b032cd57713845dd2e273a2fa3
3
+ size 86690920
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8db8e8684deb47df0c478a8f1fc626861102619f9c4d219e5e98faad8bf4d9be
3
+ size 173498123
checkpoint-200/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "processor_class": "CLIPProcessor",
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 224,
27
+ "width": 224
28
+ }
29
+ }
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2552a9c1a004336609904ae6d166ca22603d679a5f4292982515b96c708ee7
3
+ size 14645
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf6de35015d83495745d5edb65945334b61449cd6c3e3a66b09078c5823a4a26
3
+ size 1465
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 200,
3
+ "best_metric": 0.0910862535238266,
4
+ "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-200",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 200,
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": 0.94625,
15
+ "eval_loss": 0.11963150650262833,
16
+ "eval_model_preparation_time": 0.003,
17
+ "eval_runtime": 169.7911,
18
+ "eval_samples_per_second": 18.847,
19
+ "eval_steps_per_second": 2.356,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.965625,
25
+ "eval_loss": 0.0910862535238266,
26
+ "eval_model_preparation_time": 0.003,
27
+ "eval_runtime": 167.4063,
28
+ "eval_samples_per_second": 19.115,
29
+ "eval_steps_per_second": 2.389,
30
+ "step": 200
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 300,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 3,
37
+ "save_steps": 500,
38
+ "stateful_callbacks": {
39
+ "TrainerControl": {
40
+ "args": {
41
+ "should_epoch_stop": false,
42
+ "should_evaluate": false,
43
+ "should_log": false,
44
+ "should_save": true,
45
+ "should_training_stop": false
46
+ },
47
+ "attributes": {}
48
+ }
49
+ },
50
+ "total_flos": 1.24802904489984e+17,
51
+ "train_batch_size": 32,
52
+ "trial_name": null,
53
+ "trial_params": null
54
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6072cf5c917b1b93ccbdb1b8bb5ab626fca6efc4913a5ad3ed0b4a994467d8d3
3
+ size 5777
checkpoint-300/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MetaClip2ForImageClassification"
4
+ ],
5
+ "dtype": "float32",
6
+ "id2label": {
7
+ "0": "female",
8
+ "1": "male"
9
+ },
10
+ "initializer_factor": 1.0,
11
+ "label2id": {
12
+ "female": 0,
13
+ "male": 1
14
+ },
15
+ "logit_scale_init_value": 2.6592,
16
+ "model_type": "metaclip_2",
17
+ "problem_type": "single_label_classification",
18
+ "projection_dim": 384,
19
+ "text_config": {
20
+ "attention_dropout": 0.0,
21
+ "dtype": "float32",
22
+ "eos_token_id": 2,
23
+ "hidden_act": "gelu",
24
+ "hidden_size": 384,
25
+ "initializer_factor": 1.0,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 1536,
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 77,
30
+ "model_type": "metaclip_2_text_model",
31
+ "num_attention_heads": 6,
32
+ "num_hidden_layers": 12,
33
+ "projection_dim": 384,
34
+ "vocab_size": 901629
35
+ },
36
+ "transformers_version": "4.57.1",
37
+ "vision_config": {
38
+ "attention_dropout": 0.0,
39
+ "dtype": "float32",
40
+ "hidden_act": "gelu",
41
+ "hidden_size": 384,
42
+ "image_size": 224,
43
+ "initializer_factor": 1.0,
44
+ "initializer_range": 0.02,
45
+ "intermediate_size": 1536,
46
+ "layer_norm_eps": 1e-05,
47
+ "model_type": "metaclip_2_vision_model",
48
+ "num_attention_heads": 6,
49
+ "num_channels": 3,
50
+ "num_hidden_layers": 12,
51
+ "patch_size": 16,
52
+ "projection_dim": 384
53
+ }
54
+ }
checkpoint-300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3158cef230d8b630ce3ee0e5781aacff7892efb05ab92a4c8c97e248a0a2f7b
3
+ size 86690920
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6ca09834238b033c2b20aed2e1a48c229ffe51a57c9656fa67210011bce41c4
3
+ size 173498123
checkpoint-300/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "processor_class": "CLIPProcessor",
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 224,
27
+ "width": 224
28
+ }
29
+ }
checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43e192e5b64942957494df4c0ec49370730580434e17d77fb6db57f74674bbe4
3
+ size 14645
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a969d3c8e0e327dcd603078bbcf559e3c5e110c8dfbeb793a88bf86dffbb796
3
+ size 1465
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 300,
3
+ "best_metric": 0.06912863999605179,
4
+ "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-300",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 300,
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": 0.94625,
15
+ "eval_loss": 0.11963150650262833,
16
+ "eval_model_preparation_time": 0.003,
17
+ "eval_runtime": 169.7911,
18
+ "eval_samples_per_second": 18.847,
19
+ "eval_steps_per_second": 2.356,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.965625,
25
+ "eval_loss": 0.0910862535238266,
26
+ "eval_model_preparation_time": 0.003,
27
+ "eval_runtime": 167.4063,
28
+ "eval_samples_per_second": 19.115,
29
+ "eval_steps_per_second": 2.389,
30
+ "step": 200
31
+ },
32
+ {
33
+ "epoch": 3.0,
34
+ "eval_accuracy": 0.9725,
35
+ "eval_loss": 0.06912863999605179,
36
+ "eval_model_preparation_time": 0.003,
37
+ "eval_runtime": 166.4478,
38
+ "eval_samples_per_second": 19.225,
39
+ "eval_steps_per_second": 2.403,
40
+ "step": 300
41
+ }
42
+ ],
43
+ "logging_steps": 500,
44
+ "max_steps": 300,
45
+ "num_input_tokens_seen": 0,
46
+ "num_train_epochs": 3,
47
+ "save_steps": 500,
48
+ "stateful_callbacks": {
49
+ "TrainerControl": {
50
+ "args": {
51
+ "should_epoch_stop": false,
52
+ "should_evaluate": false,
53
+ "should_log": false,
54
+ "should_save": true,
55
+ "should_training_stop": true
56
+ },
57
+ "attributes": {}
58
+ }
59
+ },
60
+ "total_flos": 1.87204356734976e+17,
61
+ "train_batch_size": 32,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6072cf5c917b1b93ccbdb1b8bb5ab626fca6efc4913a5ad3ed0b4a994467d8d3
3
+ size 5777
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MetaClip2ForImageClassification"
4
+ ],
5
+ "dtype": "float32",
6
+ "id2label": {
7
+ "0": "female",
8
+ "1": "male"
9
+ },
10
+ "initializer_factor": 1.0,
11
+ "label2id": {
12
+ "female": 0,
13
+ "male": 1
14
+ },
15
+ "logit_scale_init_value": 2.6592,
16
+ "model_type": "metaclip_2",
17
+ "problem_type": "single_label_classification",
18
+ "projection_dim": 384,
19
+ "text_config": {
20
+ "attention_dropout": 0.0,
21
+ "dtype": "float32",
22
+ "eos_token_id": 2,
23
+ "hidden_act": "gelu",
24
+ "hidden_size": 384,
25
+ "initializer_factor": 1.0,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 1536,
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 77,
30
+ "model_type": "metaclip_2_text_model",
31
+ "num_attention_heads": 6,
32
+ "num_hidden_layers": 12,
33
+ "projection_dim": 384,
34
+ "vocab_size": 901629
35
+ },
36
+ "transformers_version": "4.57.1",
37
+ "vision_config": {
38
+ "attention_dropout": 0.0,
39
+ "dtype": "float32",
40
+ "hidden_act": "gelu",
41
+ "hidden_size": 384,
42
+ "image_size": 224,
43
+ "initializer_factor": 1.0,
44
+ "initializer_range": 0.02,
45
+ "intermediate_size": 1536,
46
+ "layer_norm_eps": 1e-05,
47
+ "model_type": "metaclip_2_vision_model",
48
+ "num_attention_heads": 6,
49
+ "num_channels": 3,
50
+ "num_hidden_layers": 12,
51
+ "patch_size": 16,
52
+ "projection_dim": 384
53
+ }
54
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3158cef230d8b630ce3ee0e5781aacff7892efb05ab92a4c8c97e248a0a2f7b
3
+ size 86690920
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "processor_class": "CLIPProcessor",
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 224,
27
+ "width": 224
28
+ }
29
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6072cf5c917b1b93ccbdb1b8bb5ab626fca6efc4913a5ad3ed0b4a994467d8d3
3
+ size 5777