Upload folder using huggingface_hub
Browse files- ViCLIP/ViClip-InternVid-10M-FLT.pth +3 -0
- ViCLIP/bpe_simple_vocab_16e6.txt.gz +3 -0
- aesthetic_model/emb_reader/sa_0_4_vit_l_14_linear.pth +3 -0
- amt_model/amt-s.pth +3 -0
- caption_model/tag2text_swin_14m.pth +3 -0
- clip_model/ViT-B-32.pt +3 -0
- grit_model/grit_b_densecap_objectdet.pth +3 -0
- pyiqa_model/musiq_spaq_ckpt-358bb6af.pth +3 -0
- q16/prompts.p +0 -0
- raft_model/models/raft-chairs.pth +3 -0
- raft_model/models/raft-kitti.pth +3 -0
- raft_model/models/raft-sintel.pth +3 -0
- raft_model/models/raft-small.pth +3 -0
- raft_model/models/raft-things.pth +3 -0
- retina_face_model/retinaface_resnet50_2020-07-20-f168fae3c.zip +3 -0
- sd_safety_checker/config.json +171 -0
- sd_safety_checker/preprocessor_config.json +20 -0
- sd_safety_checker/pytorch_model.bin +3 -0
- umt_model/l16_ptk710_ftk710_ftk400_f16_res224.pth +3 -0
ViCLIP/ViClip-InternVid-10M-FLT.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a4d6ad6eac6632db3693f4b97f9f8f6445b65b1e139a6fc6686150522238c56
|
3 |
+
size 1710545812
|
ViCLIP/bpe_simple_vocab_16e6.txt.gz
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:924691ac288e54409236115652ad4aa250f48203de50a9e4722a6ecd48d6804a
|
3 |
+
size 1356917
|
aesthetic_model/emb_reader/sa_0_4_vit_l_14_linear.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cd4e60f4f24ae3bcd57b847b13c1f3ba27edc28cc1a7f9ce74ee9f421243cba
|
3 |
+
size 4071
|
amt_model/amt-s.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07e7e03405c213fe4405678db9b42d05671e48c56faf6a441b99bb0047d3cf77
|
3 |
+
size 12038359
|
caption_model/tag2text_swin_14m.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ce96f0ce98f940a6680d567f66a38ccc9ca8c4e638e5f5c5c2e881a0e3502ac
|
3 |
+
size 4478705095
|
clip_model/ViT-B-32.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40d365715913c9da98579312b702a82c18be219cc2a73407c4526f58eba950af
|
3 |
+
size 353976522
|
grit_model/grit_b_densecap_objectdet.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53b6e9b3fd948eac55b574c9b6f94ad0743dff46ba449df7ac2d33009ee92ef1
|
3 |
+
size 417381733
|
pyiqa_model/musiq_spaq_ckpt-358bb6af.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:358bb6af275e28ea56821d44fb55c6cb83645db11f394d3ad65b2d149965ab50
|
3 |
+
size 108610983
|
q16/prompts.p
ADDED
Binary file (2.21 kB). View file
|
|
raft_model/models/raft-chairs.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6c75465cf995d137f89ca2e2d08594ed390befbb8859f7f65c48bcc8feb0fd7
|
3 |
+
size 21108000
|
raft_model/models/raft-kitti.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9d170362415e1a27bd8402ee966a3ddf0d60df9b2df2c0b4949f5ced490a9e6
|
3 |
+
size 21108000
|
raft_model/models/raft-sintel.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90630d2e7d488a0d3ccb5e8194524850c4c05c732ea4ff99799822c7fa5c5cbf
|
3 |
+
size 21108000
|
raft_model/models/raft-small.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7d41b9cc88442bb8aa911dbb33086dac55a226394b142937ff22d5578717332
|
3 |
+
size 3984814
|
raft_model/models/raft-things.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcfa4125d6418f4de95d84aec20a3c5f4e205101715a79f193243c186ac9a7e1
|
3 |
+
size 21108000
|
retina_face_model/retinaface_resnet50_2020-07-20-f168fae3c.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f168fae3ce6d6d3af69dd712049bfe857d3bc1422f715ac8ddfdf552ed7070ef
|
3 |
+
size 101611400
|
sd_safety_checker/config.json
ADDED
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "clip-vit-large-patch14/",
|
3 |
+
"architectures": [
|
4 |
+
"SafetyChecker"
|
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 |
+
}
|
sd_safety_checker/preprocessor_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
sd_safety_checker/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64b8393f1afd5a0c1ed2aa5f341fa7c08286839a48f3743162a76a2835c808bd
|
3 |
+
size 1216067303
|
umt_model/l16_ptk710_ftk710_ftk400_f16_res224.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfee78a03bf806fbc0c216309e8f92792011b7db6556fa860e9d869c1e69fecd
|
3 |
+
size 607024201
|