kirisame commited on
Commit
23eab1c
1 Parent(s): d126343

Remove diffusers weights

Browse files
feature_extractor/preprocessor_config.json DELETED
@@ -1,20 +0,0 @@
1
- {
2
- "crop_size": 224,
3
- "do_center_crop": true,
4
- "do_convert_rgb": true,
5
- "do_normalize": true,
6
- "do_resize": true,
7
- "feature_extractor_type": "CLIPFeatureExtractor",
8
- "image_mean": [
9
- 0.48145466,
10
- 0.4578275,
11
- 0.40821073
12
- ],
13
- "image_std": [
14
- 0.26862954,
15
- 0.26130258,
16
- 0.27577711
17
- ],
18
- "resample": 3,
19
- "size": 224
20
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model_index.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.2.4",
4
- "feature_extractor": [
5
- "transformers",
6
- "CLIPFeatureExtractor"
7
- ],
8
- "safety_checker": [
9
- "stable_diffusion",
10
- "StableDiffusionSafetyChecker"
11
- ],
12
- "text_encoder": [
13
- "transformers",
14
- "CLIPTextModel"
15
- ],
16
- "scheduler": [
17
- "diffusers",
18
- "DDIMScheduler"
19
- ],
20
- "tokenizer": [
21
- "transformers",
22
- "CLIPTokenizer"
23
- ],
24
- "unet": [
25
- "diffusers",
26
- "UNet2DConditionModel"
27
- ],
28
- "vae": [
29
- "diffusers",
30
- "AutoencoderKL"
31
- ]
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
safety_checker/config.json DELETED
@@ -1,171 +0,0 @@
1
- {
2
- "_name_or_path": "./safety_module",
3
- "architectures": [
4
- "StableDiffusionSafetyChecker"
5
- ],
6
- "initializer_factor": 1.0,
7
- "logit_scale_init_value": 2.6592,
8
- "model_type": "clip",
9
- "projection_dim": 768,
10
- "text_config": {
11
- "_name_or_path": "",
12
- "add_cross_attention": false,
13
- "architectures": null,
14
- "attention_dropout": 0.0,
15
- "bad_words_ids": null,
16
- "bos_token_id": 0,
17
- "chunk_size_feed_forward": 0,
18
- "cross_attention_hidden_size": null,
19
- "decoder_start_token_id": null,
20
- "diversity_penalty": 0.0,
21
- "do_sample": false,
22
- "dropout": 0.0,
23
- "early_stopping": false,
24
- "encoder_no_repeat_ngram_size": 0,
25
- "eos_token_id": 2,
26
- "exponential_decay_length_penalty": null,
27
- "finetuning_task": null,
28
- "forced_bos_token_id": null,
29
- "forced_eos_token_id": null,
30
- "hidden_act": "quick_gelu",
31
- "hidden_size": 768,
32
- "id2label": {
33
- "0": "LABEL_0",
34
- "1": "LABEL_1"
35
- },
36
- "initializer_factor": 1.0,
37
- "initializer_range": 0.02,
38
- "intermediate_size": 3072,
39
- "is_decoder": false,
40
- "is_encoder_decoder": false,
41
- "label2id": {
42
- "LABEL_0": 0,
43
- "LABEL_1": 1
44
- },
45
- "layer_norm_eps": 1e-05,
46
- "length_penalty": 1.0,
47
- "max_length": 20,
48
- "max_position_embeddings": 77,
49
- "min_length": 0,
50
- "model_type": "clip_text_model",
51
- "no_repeat_ngram_size": 0,
52
- "num_attention_heads": 12,
53
- "num_beam_groups": 1,
54
- "num_beams": 1,
55
- "num_hidden_layers": 12,
56
- "num_return_sequences": 1,
57
- "output_attentions": false,
58
- "output_hidden_states": false,
59
- "output_scores": false,
60
- "pad_token_id": 1,
61
- "prefix": null,
62
- "problem_type": null,
63
- "pruned_heads": {},
64
- "remove_invalid_values": false,
65
- "repetition_penalty": 1.0,
66
- "return_dict": true,
67
- "return_dict_in_generate": false,
68
- "sep_token_id": null,
69
- "task_specific_params": null,
70
- "temperature": 1.0,
71
- "tie_encoder_decoder": false,
72
- "tie_word_embeddings": true,
73
- "tokenizer_class": null,
74
- "top_k": 50,
75
- "top_p": 1.0,
76
- "torch_dtype": null,
77
- "torchscript": false,
78
- "transformers_version": "4.21.0.dev0",
79
- "typical_p": 1.0,
80
- "use_bfloat16": false,
81
- "vocab_size": 49408
82
- },
83
- "text_config_dict": {
84
- "hidden_size": 768,
85
- "intermediate_size": 3072,
86
- "num_attention_heads": 12,
87
- "num_hidden_layers": 12
88
- },
89
- "torch_dtype": "float32",
90
- "transformers_version": null,
91
- "vision_config": {
92
- "_name_or_path": "",
93
- "add_cross_attention": false,
94
- "architectures": null,
95
- "attention_dropout": 0.0,
96
- "bad_words_ids": null,
97
- "bos_token_id": null,
98
- "chunk_size_feed_forward": 0,
99
- "cross_attention_hidden_size": null,
100
- "decoder_start_token_id": null,
101
- "diversity_penalty": 0.0,
102
- "do_sample": false,
103
- "dropout": 0.0,
104
- "early_stopping": false,
105
- "encoder_no_repeat_ngram_size": 0,
106
- "eos_token_id": null,
107
- "exponential_decay_length_penalty": null,
108
- "finetuning_task": null,
109
- "forced_bos_token_id": null,
110
- "forced_eos_token_id": null,
111
- "hidden_act": "quick_gelu",
112
- "hidden_size": 1024,
113
- "id2label": {
114
- "0": "LABEL_0",
115
- "1": "LABEL_1"
116
- },
117
- "image_size": 224,
118
- "initializer_factor": 1.0,
119
- "initializer_range": 0.02,
120
- "intermediate_size": 4096,
121
- "is_decoder": false,
122
- "is_encoder_decoder": false,
123
- "label2id": {
124
- "LABEL_0": 0,
125
- "LABEL_1": 1
126
- },
127
- "layer_norm_eps": 1e-05,
128
- "length_penalty": 1.0,
129
- "max_length": 20,
130
- "min_length": 0,
131
- "model_type": "clip_vision_model",
132
- "no_repeat_ngram_size": 0,
133
- "num_attention_heads": 16,
134
- "num_beam_groups": 1,
135
- "num_beams": 1,
136
- "num_hidden_layers": 24,
137
- "num_return_sequences": 1,
138
- "output_attentions": false,
139
- "output_hidden_states": false,
140
- "output_scores": false,
141
- "pad_token_id": null,
142
- "patch_size": 14,
143
- "prefix": null,
144
- "problem_type": null,
145
- "pruned_heads": {},
146
- "remove_invalid_values": false,
147
- "repetition_penalty": 1.0,
148
- "return_dict": true,
149
- "return_dict_in_generate": false,
150
- "sep_token_id": null,
151
- "task_specific_params": null,
152
- "temperature": 1.0,
153
- "tie_encoder_decoder": false,
154
- "tie_word_embeddings": true,
155
- "tokenizer_class": null,
156
- "top_k": 50,
157
- "top_p": 1.0,
158
- "torch_dtype": null,
159
- "torchscript": false,
160
- "transformers_version": "4.21.0.dev0",
161
- "typical_p": 1.0,
162
- "use_bfloat16": false
163
- },
164
- "vision_config_dict": {
165
- "hidden_size": 1024,
166
- "intermediate_size": 4096,
167
- "num_attention_heads": 16,
168
- "num_hidden_layers": 24,
169
- "patch_size": 14
170
- }
171
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
safety_checker/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:193490b58ef62739077262e833bf091c66c29488058681ac25cf7df3d8190974
3
- size 1216061799
 
 
 
 
scheduler/scheduler_config.json DELETED
@@ -1,12 +0,0 @@
1
- {
2
- "_class_name": "DDIMScheduler",
3
- "_diffusers_version": "0.2.4",
4
- "beta_end": 0.012,
5
- "beta_schedule": "scaled_linear",
6
- "beta_start": 0.00085,
7
- "clip_sample": true,
8
- "num_train_timesteps": 1000,
9
- "set_alpha_to_one": true,
10
- "timestep_values": null,
11
- "trained_betas": null
12
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
text_encoder/config.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "_name_or_path": "openai/clip-vit-large-patch14",
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
- "torch_dtype": "float32",
22
- "transformers_version": "4.21.2",
23
- "vocab_size": 49408
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
text_encoder/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:770a47a9ffdcfda0b05506a7888ed714d06131d60267e6cf52765d61cf59fd67
3
- size 492305335
 
 
 
 
tokenizer/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
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": "<|endoftext|>",
17
- "unk_token": {
18
- "content": "<|endoftext|>",
19
- "lstrip": false,
20
- "normalized": true,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer/tokenizer_config.json DELETED
@@ -1,34 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "bos_token": {
4
- "__type": "AddedToken",
5
- "content": "<|startoftext|>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false
10
- },
11
- "do_lower_case": true,
12
- "eos_token": {
13
- "__type": "AddedToken",
14
- "content": "<|endoftext|>",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
- "errors": "replace",
21
- "model_max_length": 77,
22
- "name_or_path": "openai/clip-vit-large-patch14",
23
- "pad_token": "<|endoftext|>",
24
- "special_tokens_map_file": "./special_tokens_map.json",
25
- "tokenizer_class": "CLIPTokenizer",
26
- "unk_token": {
27
- "__type": "AddedToken",
28
- "content": "<|endoftext|>",
29
- "lstrip": false,
30
- "normalized": true,
31
- "rstrip": false,
32
- "single_word": false
33
- }
34
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
unet/config.json DELETED
@@ -1,36 +0,0 @@
1
- {
2
- "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.2.4",
4
- "act_fn": "silu",
5
- "attention_head_dim": 8,
6
- "block_out_channels": [
7
- 320,
8
- 640,
9
- 1280,
10
- 1280
11
- ],
12
- "center_input_sample": false,
13
- "cross_attention_dim": 768,
14
- "down_block_types": [
15
- "CrossAttnDownBlock2D",
16
- "CrossAttnDownBlock2D",
17
- "CrossAttnDownBlock2D",
18
- "DownBlock2D"
19
- ],
20
- "downsample_padding": 1,
21
- "flip_sin_to_cos": true,
22
- "freq_shift": 0,
23
- "in_channels": 4,
24
- "layers_per_block": 2,
25
- "mid_block_scale_factor": 1,
26
- "norm_eps": 1e-05,
27
- "norm_num_groups": 32,
28
- "out_channels": 4,
29
- "sample_size": 32,
30
- "up_block_types": [
31
- "UpBlock2D",
32
- "CrossAttnUpBlock2D",
33
- "CrossAttnUpBlock2D",
34
- "CrossAttnUpBlock2D"
35
- ]
36
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
unet/diffusion_pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8eebfab1332ba153ae9ece13169cd6839640246880ef04c664a7bc49b1ed7951
3
- size 3438354725
 
 
 
 
vae/config.json DELETED
@@ -1,28 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.2.4",
4
- "act_fn": "silu",
5
- "block_out_channels": [
6
- 128,
7
- 256,
8
- 512,
9
- 512
10
- ],
11
- "down_block_types": [
12
- "DownEncoderBlock2D",
13
- "DownEncoderBlock2D",
14
- "DownEncoderBlock2D",
15
- "DownEncoderBlock2D"
16
- ],
17
- "in_channels": 3,
18
- "latent_channels": 4,
19
- "layers_per_block": 2,
20
- "out_channels": 3,
21
- "sample_size": 512,
22
- "up_block_types": [
23
- "UpDecoderBlock2D",
24
- "UpDecoderBlock2D",
25
- "UpDecoderBlock2D",
26
- "UpDecoderBlock2D"
27
- ]
28
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vae/diffusion_pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b134cded8eb78b184aefb8805b6b572f36fa77b255c483665dda931fa0130c5
3
- size 334707217