valhalla commited on
Commit
4ff37f5
1 Parent(s): 8eae3bb

fix vision model

Browse files
image_encoder/config.json CHANGED
@@ -1,181 +1,23 @@
1
  {
2
- "_commit_hash": "2ddbd90b14bc5892c19925b15185e561bc8e5d0a",
3
- "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/diffusers/models--lambdalabs--sd-image-variations-diffusers/snapshots/2ddbd90b14bc5892c19925b15185e561bc8e5d0a/image_encoder",
4
  "architectures": [
5
- "CLIPModel"
6
  ],
 
 
 
 
 
7
  "initializer_factor": 1.0,
8
- "logit_scale_init_value": 2.6592,
9
- "model_type": "clip",
10
- "projection_dim": 768,
11
- "text_config": {
12
- "_name_or_path": "",
13
- "add_cross_attention": false,
14
- "architectures": null,
15
- "attention_dropout": 0.0,
16
- "bad_words_ids": null,
17
- "begin_suppress_tokens": null,
18
- "bos_token_id": 0,
19
- "chunk_size_feed_forward": 0,
20
- "cross_attention_hidden_size": null,
21
- "decoder_start_token_id": null,
22
- "diversity_penalty": 0.0,
23
- "do_sample": false,
24
- "dropout": 0.0,
25
- "early_stopping": false,
26
- "encoder_no_repeat_ngram_size": 0,
27
- "eos_token_id": 2,
28
- "exponential_decay_length_penalty": null,
29
- "finetuning_task": null,
30
- "forced_bos_token_id": null,
31
- "forced_eos_token_id": null,
32
- "hidden_act": "quick_gelu",
33
- "hidden_size": 768,
34
- "id2label": {
35
- "0": "LABEL_0",
36
- "1": "LABEL_1"
37
- },
38
- "initializer_factor": 1.0,
39
- "initializer_range": 0.02,
40
- "intermediate_size": 3072,
41
- "is_decoder": false,
42
- "is_encoder_decoder": false,
43
- "label2id": {
44
- "LABEL_0": 0,
45
- "LABEL_1": 1
46
- },
47
- "layer_norm_eps": 1e-05,
48
- "length_penalty": 1.0,
49
- "max_length": 20,
50
- "max_position_embeddings": 77,
51
- "min_length": 0,
52
- "model_type": "clip_text_model",
53
- "no_repeat_ngram_size": 0,
54
- "num_attention_heads": 12,
55
- "num_beam_groups": 1,
56
- "num_beams": 1,
57
- "num_hidden_layers": 12,
58
- "num_return_sequences": 1,
59
- "output_attentions": false,
60
- "output_hidden_states": false,
61
- "output_scores": false,
62
- "pad_token_id": 1,
63
- "prefix": null,
64
- "problem_type": null,
65
- "projection_dim": 512,
66
- "pruned_heads": {},
67
- "remove_invalid_values": false,
68
- "repetition_penalty": 1.0,
69
- "return_dict": true,
70
- "return_dict_in_generate": false,
71
- "sep_token_id": null,
72
- "suppress_tokens": null,
73
- "task_specific_params": null,
74
- "temperature": 1.0,
75
- "tf_legacy_loss": false,
76
- "tie_encoder_decoder": false,
77
- "tie_word_embeddings": true,
78
- "tokenizer_class": null,
79
- "top_k": 50,
80
- "top_p": 1.0,
81
- "torch_dtype": null,
82
- "torchscript": false,
83
- "transformers_version": "4.25.0.dev0",
84
- "typical_p": 1.0,
85
- "use_bfloat16": false,
86
- "vocab_size": 49408
87
- },
88
- "text_config_dict": {
89
- "hidden_size": 768,
90
- "intermediate_size": 3072,
91
- "num_attention_heads": 12,
92
- "num_hidden_layers": 12
93
- },
94
  "torch_dtype": "float32",
95
- "transformers_version": null,
96
- "vision_config": {
97
- "_name_or_path": "",
98
- "add_cross_attention": false,
99
- "architectures": null,
100
- "attention_dropout": 0.0,
101
- "bad_words_ids": null,
102
- "begin_suppress_tokens": null,
103
- "bos_token_id": null,
104
- "chunk_size_feed_forward": 0,
105
- "cross_attention_hidden_size": null,
106
- "decoder_start_token_id": null,
107
- "diversity_penalty": 0.0,
108
- "do_sample": false,
109
- "dropout": 0.0,
110
- "early_stopping": false,
111
- "encoder_no_repeat_ngram_size": 0,
112
- "eos_token_id": null,
113
- "exponential_decay_length_penalty": null,
114
- "finetuning_task": null,
115
- "forced_bos_token_id": null,
116
- "forced_eos_token_id": null,
117
- "hidden_act": "quick_gelu",
118
- "hidden_size": 1024,
119
- "id2label": {
120
- "0": "LABEL_0",
121
- "1": "LABEL_1"
122
- },
123
- "image_size": 224,
124
- "initializer_factor": 1.0,
125
- "initializer_range": 0.02,
126
- "intermediate_size": 4096,
127
- "is_decoder": false,
128
- "is_encoder_decoder": false,
129
- "label2id": {
130
- "LABEL_0": 0,
131
- "LABEL_1": 1
132
- },
133
- "layer_norm_eps": 1e-05,
134
- "length_penalty": 1.0,
135
- "max_length": 20,
136
- "min_length": 0,
137
- "model_type": "clip_vision_model",
138
- "no_repeat_ngram_size": 0,
139
- "num_attention_heads": 16,
140
- "num_beam_groups": 1,
141
- "num_beams": 1,
142
- "num_channels": 3,
143
- "num_hidden_layers": 24,
144
- "num_return_sequences": 1,
145
- "output_attentions": false,
146
- "output_hidden_states": false,
147
- "output_scores": false,
148
- "pad_token_id": null,
149
- "patch_size": 14,
150
- "prefix": null,
151
- "problem_type": null,
152
- "projection_dim": 512,
153
- "pruned_heads": {},
154
- "remove_invalid_values": false,
155
- "repetition_penalty": 1.0,
156
- "return_dict": true,
157
- "return_dict_in_generate": false,
158
- "sep_token_id": null,
159
- "suppress_tokens": null,
160
- "task_specific_params": null,
161
- "temperature": 1.0,
162
- "tf_legacy_loss": false,
163
- "tie_encoder_decoder": false,
164
- "tie_word_embeddings": true,
165
- "tokenizer_class": null,
166
- "top_k": 50,
167
- "top_p": 1.0,
168
- "torch_dtype": null,
169
- "torchscript": false,
170
- "transformers_version": "4.25.0.dev0",
171
- "typical_p": 1.0,
172
- "use_bfloat16": false
173
- },
174
- "vision_config_dict": {
175
- "hidden_size": 1024,
176
- "intermediate_size": 4096,
177
- "num_attention_heads": 16,
178
- "num_hidden_layers": 24,
179
- "patch_size": 14
180
- }
181
  }
 
1
  {
2
+ "_name_or_path": "lambdalabs/sd-image-variations-diffusers/image_encoder",
 
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": 512,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "torch_dtype": "float32",
22
+ "transformers_version": "4.25.0.dev0"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  }
image_encoder/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ee8b5598b8b3dba3e335c2300fc6124538697e687836134cf3ae01eb19089f0
3
- size 1710668513
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0abb19a705a48a11cf093ca7079e1e4c8be1b50dc7c64d5d6b79d98f50f57c6
3
+ size 1215999471
safety_checker/config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "_commit_hash": "2ddbd90b14bc5892c19925b15185e561bc8e5d0a",
3
- "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/diffusers/models--lambdalabs--sd-image-variations-diffusers/snapshots/2ddbd90b14bc5892c19925b15185e561bc8e5d0a/safety_checker",
4
  "architectures": [
5
  "StableDiffusionSafetyChecker"
6
  ],
 
1
  {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "lambdalabs/sd-image-variations-diffusers/safety_checker",
4
  "architectures": [
5
  "StableDiffusionSafetyChecker"
6
  ],
unet/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.8.0.dev0",
4
- "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/diffusers/models--lambdalabs--sd-image-variations-diffusers/snapshots/2ddbd90b14bc5892c19925b15185e561bc8e5d0a/unet",
5
  "act_fn": "silu",
6
  "attention_head_dim": 8,
7
  "block_out_channels": [
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.8.0.dev0",
4
+ "_name_or_path": "lambdalabs/sd-image-variations-diffusers/unet",
5
  "act_fn": "silu",
6
  "attention_head_dim": 8,
7
  "block_out_channels": [
vae/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
  "_diffusers_version": "0.8.0.dev0",
4
- "_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/diffusers/models--lambdalabs--sd-image-variations-diffusers/snapshots/2ddbd90b14bc5892c19925b15185e561bc8e5d0a/vae",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
  "_diffusers_version": "0.8.0.dev0",
4
+ "_name_or_path": "lambdalabs/sd-image-variations-diffusers/vae",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,