nijatzeynalov commited on
Commit
85becef
1 Parent(s): 975fb6f

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bigbird-pegasus-large-arxiv",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "BigBirdForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "attention_type": "block_sparse",
11
+ "block_size": 64,
12
+ "bos_token_id": 2,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 16,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "encoder_attention_heads": 16,
22
+ "encoder_ffn_dim": 4096,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 16,
25
+ "eos_token_id": 1,
26
+ "gradient_checkpointing": false,
27
+ "hidden_act": "gelu_new",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "Email",
32
+ "1": "Website"
33
+ },
34
+ "init_std": 0.02,
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "Email": 0,
40
+ "Website": 1
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "length_penalty": 0.8,
44
+ "max_length": 256,
45
+ "max_position_embeddings": 4096,
46
+ "model_type": "big_bird",
47
+ "num_attention_heads": 12,
48
+ "num_beams": 5,
49
+ "num_hidden_layers": 16,
50
+ "num_random_blocks": 3,
51
+ "pad_token_id": 0,
52
+ "problem_type": "single_label_classification",
53
+ "rescale_embeddings": false,
54
+ "scale_embedding": true,
55
+ "sep_token_id": 66,
56
+ "tokenizer_class": "PegasusTokenizer",
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.37.2",
59
+ "type_vocab_size": 2,
60
+ "use_bias": false,
61
+ "use_cache": true,
62
+ "vocab_size": 96103
63
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadbaa1a88c6f4eceebdece66d2efff7ff93b108af13ba6356465fff69a60683
3
+ size 766056640
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
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": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": true,
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
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe1b40df7e8825709c0172639c47338a68d5622e9e3b6cc0fae516537cae738b
3
+ size 1915455
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "65": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "66": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "67": {
44
+ "content": "[MASK]",
45
+ "lstrip": true,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "105": {
52
+ "content": "<unk>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [],
61
+ "bos_token": "<s>",
62
+ "clean_up_tokenization_spaces": true,
63
+ "cls_token": "[CLS]",
64
+ "eos_token": "</s>",
65
+ "mask_token": "[MASK]",
66
+ "mask_token_sent": null,
67
+ "max_length": 512,
68
+ "model_max_length": 4096,
69
+ "offset": 0,
70
+ "pad_token": "<pad>",
71
+ "sep_token": "[SEP]",
72
+ "tokenizer_class": "PegasusTokenizer",
73
+ "unk_token": "<unk>"
74
+ }