Xenova HF staff commited on
Commit
9b83c04
·
verified ·
1 Parent(s): b803716

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_label_trainable_num_channels": 1024,
4
+ "_name_or_path": "hf-internal-testing/tiny-random-PerceiverForMaskedLM",
5
+ "architectures": [
6
+ "PerceiverForMaskedLM"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "audio_samples_per_frame": 200,
10
+ "cross_attention_shape_for_attention": "kv",
11
+ "cross_attention_widening_factor": 4,
12
+ "d_latents": 20,
13
+ "d_model": 768,
14
+ "hidden_act": "gelu",
15
+ "id2label": {
16
+ "0": "LABEL_0",
17
+ "1": "LABEL_1",
18
+ "2": "LABEL_2"
19
+ },
20
+ "image_size": 32,
21
+ "initializer_range": 0.02,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 40,
29
+ "model_type": "perceiver",
30
+ "num_blocks": 1,
31
+ "num_cross_attention_heads": 1,
32
+ "num_frames": 5,
33
+ "num_latents": 10,
34
+ "num_self_attends_per_block": 2,
35
+ "num_self_attention_heads": 1,
36
+ "output_num_channels": 512,
37
+ "output_shape": [
38
+ 1,
39
+ 16,
40
+ 224,
41
+ 224
42
+ ],
43
+ "qk_channels": 20,
44
+ "samples_per_patch": 20,
45
+ "self_attention_widening_factor": 4,
46
+ "train_size": [
47
+ 20,
48
+ 20
49
+ ],
50
+ "transformers_version": "4.48.2",
51
+ "use_query_residual": true,
52
+ "v_channels": 20,
53
+ "vocab_size": 262
54
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35baeed4f7f89f5c2ff59921c9f6e60748ec1a4c5af1d77ef43cb6d88e219b9
3
+ size 10113794
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 32,
4
+ "width": 32
5
+ },
6
+ "do_center_crop": true,
7
+ "do_normalize": true,
8
+ "do_rescale": true,
9
+ "do_resize": true,
10
+ "image_mean": [
11
+ 0.485,
12
+ 0.456,
13
+ 0.406
14
+ ],
15
+ "image_processor_type": "PerceiverFeatureExtractor",
16
+ "image_std": [
17
+ 0.229,
18
+ 0.224,
19
+ 0.225
20
+ ],
21
+ "resample": 3,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "height": 32,
25
+ "width": 32
26
+ }
27
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[BOS]",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[EOS]",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[BOS]",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[EOS]",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[MASK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[CLS]",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[SEP]",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "[BOS]",
53
+ "clean_up_tokenization_spaces": false,
54
+ "cls_token": "[CLS]",
55
+ "eos_token": "[EOS]",
56
+ "extra_special_tokens": {},
57
+ "mask_token": "[MASK]",
58
+ "model_max_length": 40,
59
+ "pad_token": "[PAD]",
60
+ "sep_token": "[SEP]",
61
+ "tokenizer_class": "PerceiverTokenizer"
62
+ }