Hugging Face's logo

Aya168
/
instruct-pix2pix-model-20const

Diffusers
TensorBoard
Safetensors
StableDiffusionInstructPix2PixImagePipeline
Model card Files
xet
 Metrics Community
Aya168 commited on
Commit
c5544f3
·
verified ·
1 Parent(s): e33ec81

End of training

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. emb_opt.pt +3 -0
  2. feature_extractor/preprocessor_config.json +27 -0
  3. image_encoder/config.json +23 -0
  4. image_encoder/model.safetensors +3 -0
  5. logs/instruct-pix2pix/1732792153.8084922/events.out.tfevents.1732792153.plato2.94307.1 +3 -0
  6. logs/instruct-pix2pix/1732792153.8161108/hparams.yml +51 -0
  7. logs/instruct-pix2pix/1732792343.685541/events.out.tfevents.1732792343.plato2.95007.1 +3 -0
  8. logs/instruct-pix2pix/1732792343.6977658/hparams.yml +51 -0
  9. logs/instruct-pix2pix/1732792499.6100707/events.out.tfevents.1732792499.plato2.95576.1 +3 -0
  10. logs/instruct-pix2pix/1732792499.6172585/hparams.yml +51 -0
  11. logs/instruct-pix2pix/1732792871.305817/events.out.tfevents.1732792871.plato2.96605.1 +3 -0
  12. logs/instruct-pix2pix/1732792871.313255/hparams.yml +51 -0
  13. logs/instruct-pix2pix/1732793143.7092247/events.out.tfevents.1732793143.plato2.97408.1 +3 -0
  14. logs/instruct-pix2pix/1732793143.7158968/hparams.yml +51 -0
  15. logs/instruct-pix2pix/1732793314.0639427/events.out.tfevents.1732793314.plato2.98497.1 +3 -0
  16. logs/instruct-pix2pix/1732793314.070753/hparams.yml +51 -0
  17. logs/instruct-pix2pix/1732793839.7469757/events.out.tfevents.1732793839.plato2.100647.1 +3 -0
  18. logs/instruct-pix2pix/1732793839.8545504/hparams.yml +51 -0
  19. logs/instruct-pix2pix/1732794036.2384422/events.out.tfevents.1732794036.plato2.101399.1 +3 -0
  20. logs/instruct-pix2pix/1732794036.2455816/hparams.yml +51 -0
  21. logs/instruct-pix2pix/1732794094.0906012/events.out.tfevents.1732794094.plato2.101801.1 +3 -0
  22. logs/instruct-pix2pix/1732794094.0974922/hparams.yml +51 -0
  23. logs/instruct-pix2pix/1732794538.9346223/events.out.tfevents.1732794538.plato2.103060.1 +3 -0
  24. logs/instruct-pix2pix/1732794539.09479/hparams.yml +51 -0
  25. logs/instruct-pix2pix/1732795447.7784283/events.out.tfevents.1732795447.plato2.107176.1 +3 -0
  26. logs/instruct-pix2pix/1732795447.8243535/hparams.yml +51 -0
  27. logs/instruct-pix2pix/1732796054.0223882/events.out.tfevents.1732796054.plato2.107818.1 +3 -0
  28. logs/instruct-pix2pix/1732796054.0844412/hparams.yml +51 -0
  29. logs/instruct-pix2pix/1732813377.6835806/events.out.tfevents.1732813377.plato2.160308.1 +3 -0
  30. logs/instruct-pix2pix/1732813377.6916652/hparams.yml +51 -0
  31. logs/instruct-pix2pix/events.out.tfevents.1732792153.plato2.94307.0 +3 -0
  32. logs/instruct-pix2pix/events.out.tfevents.1732792343.plato2.95007.0 +3 -0
  33. logs/instruct-pix2pix/events.out.tfevents.1732792499.plato2.95576.0 +3 -0
  34. logs/instruct-pix2pix/events.out.tfevents.1732792871.plato2.96605.0 +3 -0
  35. logs/instruct-pix2pix/events.out.tfevents.1732793143.plato2.97408.0 +3 -0
  36. logs/instruct-pix2pix/events.out.tfevents.1732793314.plato2.98497.0 +3 -0
  37. logs/instruct-pix2pix/events.out.tfevents.1732793839.plato2.100647.0 +3 -0
  38. logs/instruct-pix2pix/events.out.tfevents.1732794036.plato2.101399.0 +3 -0
  39. logs/instruct-pix2pix/events.out.tfevents.1732794094.plato2.101801.0 +3 -0
  40. logs/instruct-pix2pix/events.out.tfevents.1732794538.plato2.103060.0 +3 -0
  41. logs/instruct-pix2pix/events.out.tfevents.1732795446.plato2.107176.0 +3 -0
  42. logs/instruct-pix2pix/events.out.tfevents.1732796053.plato2.107818.0 +3 -0
  43. logs/instruct-pix2pix/events.out.tfevents.1732813377.plato2.160308.0 +3 -0
  44. model_index.json +38 -0
  45. scheduler/scheduler_config.json +16 -0
  46. text_encoder/config.json +25 -0
  47. text_encoder/model.safetensors +3 -0
  48. tokenizer/merges.txt +0 -0
  49. tokenizer/special_tokens_map.json +30 -0
  50. tokenizer/tokenizer_config.json +30 -0
emb_opt.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51a25cff58b5aee4c9cc5153721a55b0920b97af90281731a3e72c9b7145eb37
3
+ size 19689394
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
image_encoder/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-large-patch14",
3
+ "architectures": [
4
+ "CLIPVisionModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "quick_gelu",
9
+ "hidden_size": 1024,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 24,
19
+ "patch_size": 14,
20
+ "projection_dim": 768,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.43.4"
23
+ }
image_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b33d2a3a643650857672e880ccf73adbaf114fbbadec36d142ee9d48af7e20
3
+ size 1215912728
logs/instruct-pix2pix/1732792153.8084922/events.out.tfevents.1732792153.plato2.94307.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc13c9d0f5becb432417060cf06f5976a22be8982f630c9c0517885f7397c8e9
3
+ size 2400
logs/instruct-pix2pix/1732792153.8161108/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Aya168/project_from_PIPE
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 29
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732792343.685541/events.out.tfevents.1732792343.plato2.95007.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31297b6d7397af1866bd117e1754ef08f5f75e9752f8802f18f1f2bc65e97a0c
3
+ size 2400
logs/instruct-pix2pix/1732792343.6977658/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Aya168/project_from_PIPE
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 29
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732792499.6100707/events.out.tfevents.1732792499.plato2.95576.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6936bb146e7e1a4d9435bc88680dec5caa7a966f0706325a3a8cdc370559d6e3
3
+ size 2400
logs/instruct-pix2pix/1732792499.6172585/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Aya168/project_from_PIPE
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 29
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732792871.305817/events.out.tfevents.1732792871.plato2.96605.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8345fc9f7b97d1ec5a72d020233889b838c714730a36370778a05e2f55afe05a
3
+ size 2400
logs/instruct-pix2pix/1732792871.313255/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Aya168/project_from_PIPE
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 29
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732793143.7092247/events.out.tfevents.1732793143.plato2.97408.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3205c3099a274540091c838acc18eb16d5047c25dc734f396ed5266c837f318
3
+ size 2400
logs/instruct-pix2pix/1732793143.7158968/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Aya168/project_from_PIPE
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 29
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732793314.0639427/events.out.tfevents.1732793314.plato2.98497.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afbc8b018a9e36c15ca32f9a0a2fbc668605726af1e732ac88c0e1bbd714c1a8
3
+ size 2400
logs/instruct-pix2pix/1732793314.070753/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Aya168/project_from_PIPE
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25000
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 29
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732793839.7469757/events.out.tfevents.1732793839.plato2.100647.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26670d01dceef2cee9150e9d14dff1551d12be9307703cc548ff111a8b1ea306
3
+ size 2402
logs/instruct-pix2pix/1732793839.8545504/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Aya168/project_from_PIPE
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25000
27
+ mixed_precision: fp16
28
+ non_ema_revision: null
29
+ num_train_epochs: 29
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732794036.2384422/events.out.tfevents.1732794036.plato2.101399.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f460b85c997c2143af14b82c366b9e387abb22aaf95677e6180a029335586dfc
3
+ size 2402
logs/instruct-pix2pix/1732794036.2455816/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Aya168/project_from_PIPE
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25000
27
+ mixed_precision: fp16
28
+ non_ema_revision: null
29
+ num_train_epochs: 29
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732794094.0906012/events.out.tfevents.1732794094.plato2.101801.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58845cabf03c278f80717284265fd58371b74c4054f4a625e74d8f1035188fc9
3
+ size 2402
logs/instruct-pix2pix/1732794094.0974922/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Aya168/project_from_PIPE
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25000
27
+ mixed_precision: fp16
28
+ non_ema_revision: null
29
+ num_train_epochs: 29
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732794538.9346223/events.out.tfevents.1732794538.plato2.103060.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b55fd115e92074fb77cefd7ddc9b41b531c8755ae389a3ea88e86a5ec924db
3
+ size 2402
logs/instruct-pix2pix/1732794539.09479/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Aya168/project_from_PIPE
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25000
27
+ mixed_precision: fp16
28
+ non_ema_revision: null
29
+ num_train_epochs: 29
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732795447.7784283/events.out.tfevents.1732795447.plato2.107176.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40f6e334cee0dc64ba6ca65c493b044516cd24afaa424e386bd7534e424f005
3
+ size 2402
logs/instruct-pix2pix/1732795447.8243535/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Aya168/project_from_PIPE
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25000
27
+ mixed_precision: fp16
28
+ non_ema_revision: null
29
+ num_train_epochs: 29
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732796054.0223882/events.out.tfevents.1732796054.plato2.107818.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704aaa7170def7e821e35a7d2fb941188ae2e38b079d228e2af816453fea2c88
3
+ size 2412
logs/instruct-pix2pix/1732796054.0844412/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: ADT1999/project_from_PIPE_extended
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25000
27
+ mixed_precision: fp16
28
+ non_ema_revision: null
29
+ num_train_epochs: 12
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/1732813377.6835806/events.out.tfevents.1732813377.plato2.160308.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17e6fe5da6215fdf858d66f2ba446b36841c769752fec686921f35ac01bb4d80
3
+ size 2400
logs/instruct-pix2pix/1732813377.6916652/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Aya168/project_from_PIPE
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 2
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
19
+ learning_rate: 5.0e-05
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 500
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 25
27
+ mixed_precision: 'no'
28
+ non_ema_revision: null
29
+ num_train_epochs: 1
30
+ num_validation_images: 4
31
+ object_image_column: object_image
32
+ original_image_column: original_image
33
+ output_dir: instruct-pix2pix-model-20const
34
+ pretrained_model_name_or_path: ''
35
+ push_to_hub: true
36
+ random_flip: true
37
+ report_to: tensorboard
38
+ resolution: 224
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: 42
43
+ target_image_column: target_image
44
+ train_batch_size: 8
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ val_image_url2: null
50
+ validation_epochs: 1
51
+ variant: null
logs/instruct-pix2pix/events.out.tfevents.1732792153.plato2.94307.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45fe12d1508a12ec92cce7f111ab70ebd10fc0315b8a83bef5214e9f9658ce0a
3
+ size 184
logs/instruct-pix2pix/events.out.tfevents.1732792343.plato2.95007.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af4c00ca0d2dddad26576cf08ac8c06a6fc65536a714560bc188f1f7278e3bba
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1732792499.plato2.95576.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bae9096a4163a4991d4476bb8450bd3cdc834582b7d987dcc779a0eb9f347ab1
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1732792871.plato2.96605.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee25b693bc0791b91b4f404ece4c794780fd2fc990308ffb7f405d43f34b29e4
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1732793143.plato2.97408.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1559c6481f20c6190601256547cde2a8fd10fe5c12b356c6d4d20c495e1b3412
3
+ size 568
logs/instruct-pix2pix/events.out.tfevents.1732793314.plato2.98497.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b40a18ede803a2e94166b82cf7ece365ce49980631e821ec8a6f8ae34a23aa08
3
+ size 328
logs/instruct-pix2pix/events.out.tfevents.1732793839.plato2.100647.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6690b608e08dc1f16fa9a4f63be0b0d87a34fec7eaa7c7e86f080bc80c8dc8b
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1732794036.plato2.101399.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9c43ff534471a71b4ffb84fbce005765492b74f49e7db592d83364244e34d7d
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1732794094.plato2.101801.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d50a273017b801453826cb75f967bd183ff4896463e59885fcc2129ca875caac
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1732794538.plato2.103060.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6d4ab75d129bf7b6e0440be945ae0ae6c6777b3537b868d239c93a049009e34
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1732795446.plato2.107176.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6f929ddd66248c1164f17c2f4b0c6ee3fffd68170b173fe87c0dd5f6ed2755
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1732796053.plato2.107818.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a6d6af5f802ff7aad040526b375617581145ad93c23f39b336064fc0832f9bf
3
+ size 88
logs/instruct-pix2pix/events.out.tfevents.1732813377.plato2.160308.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aba37cbe07bb4616b0bc2c627b8706680a679c347aaeb7c593587e9083f0f9a2
3
+ size 1288
model_index.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionInstructPix2PixImagePipeline",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "paint-by-inpaint/add-base",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "image_encoder": [
10
+ "transformers",
11
+ "CLIPVisionModelWithProjection"
12
+ ],
13
+ "requires_safety_checker": true,
14
+ "safety_checker": [
15
+ null,
16
+ null
17
+ ],
18
+ "scheduler": [
19
+ "diffusers",
20
+ "EulerAncestralDiscreteScheduler"
21
+ ],
22
+ "text_encoder": [
23
+ "transformers",
24
+ "CLIPTextModel"
25
+ ],
26
+ "tokenizer": [
27
+ "transformers",
28
+ "CLIPTokenizer"
29
+ ],
30
+ "unet": [
31
+ "diffusers",
32
+ "UNet2DConditionModel"
33
+ ],
34
+ "vae": [
35
+ "diffusers",
36
+ "AutoencoderKL"
37
+ ]
38
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "EulerAncestralDiscreteScheduler",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "epsilon",
10
+ "rescale_betas_zero_snr": false,
11
+ "set_alpha_to_one": false,
12
+ "skip_prk_steps": true,
13
+ "steps_offset": 1,
14
+ "timestep_spacing": "leading",
15
+ "trained_betas": null
16
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/aya.sp/.cache/huggingface/hub/models--paint-by-inpaint--add-base/snapshots/79753a54092b836c77292b592f5c8c2e884728ef/text_encoder",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "quick_gelu",
11
+ "hidden_size": 768,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 768,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.43.4",
24
+ "vocab_size": 49408
25
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c3d6454dd2d23414b56aa1b5858a72487a656937847b6fea8d0606d7a42cdbc
3
+ size 492265168
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|startoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "do_lower_case": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "errors": "replace",
26
+ "model_max_length": 77,
27
+ "pad_token": "<|endoftext|>",
28
+ "tokenizer_class": "CLIPTokenizer",
29
+ "unk_token": "<|endoftext|>"
30
+ }