Hugging Face's logo

hf-tiny-v2
/
tiny-random-PeAudioVideoEncoder

Safetensors
pe_audio_video_encoder
Model card Files
xet
 Community
hf-transformers-bot commited on
Commit
5f647cc
·
verified ·
1 Parent(s): 2629391

Update tiny models for PeAudioVideoEncoder

Browse files
Files changed (6) hide show
  1. config.json +137 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +9 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +19 -0
  6. video_preprocessor_config.json +27 -0
config.json ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PeAudioVideoEncoder"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "audio_config": {
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dac_config": {
11
+ "_name_or_path": "",
12
+ "architectures": null,
13
+ "chunk_size_feed_forward": 0,
14
+ "codebook_dim": 32,
15
+ "codebook_loss_weight": 1.0,
16
+ "codebook_size": 512,
17
+ "commitment_loss_weight": 0.25,
18
+ "decoder_hidden_size": 16,
19
+ "downsampling_ratios": [
20
+ 2,
21
+ 4,
22
+ 4
23
+ ],
24
+ "dtype": null,
25
+ "encoder_hidden_size": 16,
26
+ "hidden_size": 128,
27
+ "hop_length": 32,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1"
31
+ },
32
+ "is_encoder_decoder": false,
33
+ "label2id": {
34
+ "LABEL_0": 0,
35
+ "LABEL_1": 1
36
+ },
37
+ "model_type": "dac",
38
+ "n_codebooks": 6,
39
+ "output_attentions": false,
40
+ "output_hidden_states": false,
41
+ "problem_type": null,
42
+ "quantizer_dropout": 0.0,
43
+ "return_dict": true,
44
+ "sampling_rate": 16000,
45
+ "upsampling_ratios": [
46
+ 4,
47
+ 4,
48
+ 2
49
+ ]
50
+ },
51
+ "head_dim": 128,
52
+ "hidden_act": "silu",
53
+ "hidden_size": 32,
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 37,
56
+ "max_position_embeddings": 512,
57
+ "max_window_layers": 28,
58
+ "model_type": "pe_audio_encoder",
59
+ "num_attention_heads": 2,
60
+ "num_hidden_layers": 2,
61
+ "num_key_value_heads": 2,
62
+ "rms_norm_eps": 1e-05,
63
+ "rope_parameters": {
64
+ "rope_theta": 20000,
65
+ "rope_type": "default"
66
+ }
67
+ },
68
+ "dtype": "float32",
69
+ "head_dim": 128,
70
+ "hidden_act": "silu",
71
+ "hidden_size": 32,
72
+ "initializer_range": 0.02,
73
+ "intermediate_size": 37,
74
+ "max_position_embeddings": 512,
75
+ "max_window_layers": 28,
76
+ "model_type": "pe_audio_video_encoder",
77
+ "num_attention_heads": 2,
78
+ "num_hidden_layers": 2,
79
+ "num_key_value_heads": 2,
80
+ "rms_norm_eps": 1e-05,
81
+ "rope_parameters": {
82
+ "rope_theta": 20000,
83
+ "rope_type": "default"
84
+ },
85
+ "transformers_version": "5.16.0.dev0",
86
+ "video_config": {
87
+ "attention_bias": false,
88
+ "attention_dropout": 0.0,
89
+ "head_dim": 128,
90
+ "hidden_act": "silu",
91
+ "hidden_size": 32,
92
+ "initializer_range": 0.02,
93
+ "intermediate_size": 37,
94
+ "max_position_embeddings": 512,
95
+ "max_window_layers": 28,
96
+ "model_type": "pe_video_encoder",
97
+ "num_attention_heads": 2,
98
+ "num_hidden_layers": 2,
99
+ "num_key_value_heads": 2,
100
+ "rms_norm_eps": 1e-05,
101
+ "rope_parameters": {
102
+ "rope_theta": 20000,
103
+ "rope_type": "default"
104
+ },
105
+ "vision_config": {
106
+ "_name_or_path": "",
107
+ "architecture": "vit_pe_core_large_patch14_336",
108
+ "architectures": null,
109
+ "chunk_size_feed_forward": 0,
110
+ "do_pooling": true,
111
+ "dtype": null,
112
+ "global_pool": "map",
113
+ "initializer_range": 0.02,
114
+ "is_encoder_decoder": false,
115
+ "label_names": [
116
+ "LABEL_0",
117
+ "LABEL_1",
118
+ "LABEL_2",
119
+ "LABEL_3"
120
+ ],
121
+ "model_args": {
122
+ "depth": 2,
123
+ "embed_dim": 64,
124
+ "img_size": [
125
+ 14,
126
+ 14
127
+ ]
128
+ },
129
+ "model_type": "timm_wrapper",
130
+ "num_classes": 4,
131
+ "output_attentions": false,
132
+ "output_hidden_states": false,
133
+ "problem_type": null,
134
+ "return_dict": true
135
+ }
136
+ }
137
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb86e6809ccae97cd01d480f23025e1b67630d2afaa10466b944990eb815846e
3
+ size 2849640
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
+ }