hf-transformers-bot HF Staff commited on
Commit
3022bff
·
verified ·
1 Parent(s): 2bdd2b6

Update tiny models for CLIPVisionModel

Browse files
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPVisionModel"
4
+ ],
5
+ "attention_dropout": 0.1,
6
+ "dropout": 0.1,
7
+ "dtype": "float32",
8
+ "hidden_act": "quick_gelu",
9
+ "hidden_size": 32,
10
+ "image_size": 30,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 37,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 4,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 2,
19
+ "patch_size": 2,
20
+ "projection_dim": 32,
21
+ "transformers_version": "5.16.0.dev0"
22
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff7af6392e400a901804a7c98f8932822f2db310ec8d0d7873423084ccb4d36
3
+ size 89192
preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "longest_edge": 30,
4
+ "shortest_edge": 30
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
+ "longest_edge": 30,
26
+ "shortest_edge": 30
27
+ }
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|startoftext|>",
5
+ "do_lower_case": true,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "is_local": true,
9
+ "local_files_only": false,
10
+ "model_max_length": 77,
11
+ "pad_token": "<|endoftext|>",
12
+ "tokenizer_class": "CLIPTokenizer",
13
+ "unk_token": "<|endoftext|>"
14
+ }