hf-transformers-bot commited on
Commit
ce49848
·
verified ·
1 Parent(s): 36de590

Update tiny models for PeVideoEncoder

Browse files
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PeVideoEncoder"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "float32",
8
+ "head_dim": 16,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 32,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 37,
13
+ "max_position_embeddings": 512,
14
+ "max_window_layers": 28,
15
+ "model_type": "pe_video_encoder",
16
+ "num_attention_heads": 2,
17
+ "num_hidden_layers": 2,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_parameters": {
21
+ "rope_theta": 20000,
22
+ "rope_type": "default"
23
+ },
24
+ "transformers_version": "5.16.0.dev0",
25
+ "vision_config": {
26
+ "architecture": "vit_pe_core_large_patch14_336",
27
+ "do_pooling": true,
28
+ "global_pool": "map",
29
+ "initializer_range": 0.02,
30
+ "label_names": [
31
+ "LABEL_0",
32
+ "LABEL_1",
33
+ "LABEL_2",
34
+ "LABEL_3"
35
+ ],
36
+ "model_args": {
37
+ "depth": 2,
38
+ "embed_dim": 64,
39
+ "img_size": [
40
+ 14,
41
+ 14
42
+ ]
43
+ },
44
+ "model_type": "timm_wrapper",
45
+ "num_classes": 4
46
+ }
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f757372b857e03e7e7a38f60d88af7cd2065a721dc311262eb1ba18cae95407
3
+ size 858232
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor_type": "PeAudioFeatureExtractor",
3
+ "feature_size": 1,
4
+ "hop_length": 1920,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 48000
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "extra_special_tokens": [],
6
+ "is_local": true,
7
+ "local_files_only": false,
8
+ "mask_token": "[MASK]",
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 512,
14
+ "pad_token": "[PAD]",
15
+ "processor_class": "PeAudioVideoProcessor",
16
+ "sep_token": "[SEP]",
17
+ "tokenizer_class": "TokenizersBackend",
18
+ "unk_token": "[UNK]"
19
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_format": "channels_first",
3
+ "default_to_square": true,
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "do_sample_frames": false,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "resample": 2,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "return_metadata": false,
22
+ "size": {
23
+ "height": 336,
24
+ "width": 336
25
+ },
26
+ "video_processor_type": "PeVideoVideoProcessor"
27
+ }