Zineng Tang commited on
Commit
00b4b42
1 Parent(s): 36e5f79

Upload 2 files

Browse files
tvlt-base/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "TVLTForPreTraining"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "audio_mask_ratio": 0.15,
7
+ "audio_patch_size": [
8
+ 16,
9
+ 16
10
+ ],
11
+ "audio_size": 2048,
12
+ "decoder_hidden_size": 512,
13
+ "decoder_intermediate_size": 2048,
14
+ "decoder_num_attention_heads": 8,
15
+ "decoder_num_hidden_layers": 8,
16
+ "feature_size": 128,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.0,
19
+ "hidden_size": 768,
20
+ "id2label": {
21
+ "0": "LABEL_0"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "model_type": "tvlt",
30
+ "norm_pix_loss": true,
31
+ "num_attention_heads": 12,
32
+ "num_audio_channels": 1,
33
+ "num_frames": 8,
34
+ "num_hidden_layers": 12,
35
+ "num_pixel_channels": 3,
36
+ "pixel_mask_ratio": 0.75,
37
+ "pixel_patch_size": 16,
38
+ "pixel_size": 224,
39
+ "qkv_bias": true,
40
+ "task_mae": true,
41
+ "task_matching": true,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.25.0.dev0",
44
+ "use_mean_pooling": false
45
+ }
tvlt-base/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd3860d5503afaf66676f41953905bef040b57be4b6e1eecc184d47ad986ac23
3
+ size 456759425