Hugging Face's logo

salmalik
/
bb_para_v2

Token Classification
Transformers
PyTorch
big_bird
Inference Endpoints
Model card Files Community
salmalik commited on
Commit
a3a439e
•
1 Parent(s): 40a3925

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +42 -0
  2. pytorch_model.bin +3 -0
  3. special_tokens_map.json +51 -0
  4. spiece.model +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +63 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bigbird-roberta-base",
3
+ "architectures": [
4
+ "BigBirdForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attention_type": "block_sparse",
8
+ "block_size": 64,
9
+ "bos_token_id": 1,
10
+ "classifier_dropout": null,
11
+ "eos_token_id": 2,
12
+ "gradient_checkpointing": false,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "Body",
18
+ "1": "Start"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "Body": 0,
24
+ "Start": 1
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 4096,
28
+ "model_type": "big_bird",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "num_random_blocks": 3,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "rescale_embeddings": false,
35
+ "sep_token_id": 66,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.25.1",
38
+ "type_vocab_size": 2,
39
+ "use_bias": true,
40
+ "use_cache": true,
41
+ "vocab_size": 50358
42
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c198f83d158467741c6c56776992a0faeb1655d6c22883b72346b8a667205ad1
3
+ size 509981037
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:fdc81e1fc9d42e0c08b86d5b280d05d7c5e9747c4231c648f2b56b8e1d893c82
3
+ size 845731
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "cls_token": {
11
+ "__type": "AddedToken",
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "__type": "AddedToken",
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "mask_token": {
27
+ "__type": "AddedToken",
28
+ "content": "[MASK]",
29
+ "lstrip": true,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "model_max_length": 4096,
35
+ "name_or_path": "google/bigbird-roberta-base",
36
+ "pad_token": {
37
+ "__type": "AddedToken",
38
+ "content": "<pad>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "sep_token": {
45
+ "__type": "AddedToken",
46
+ "content": "[SEP]",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ "sp_model_kwargs": {},
53
+ "special_tokens_map_file": "/home/hcymm2/.cache/huggingface/hub/models--google--bigbird-roberta-base/snapshots/5a145f7852cba9bd431386a58137bf8a29903b90/special_tokens_map.json",
54
+ "tokenizer_class": "BigBirdTokenizer",
55
+ "unk_token": {
56
+ "__type": "AddedToken",
57
+ "content": "<unk>",
58
+ "lstrip": false,
59
+ "normalized": true,
60
+ "rstrip": false,
61
+ "single_word": false
62
+ }
63
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f896fcda7f30d0ab15fe57e592e280c2800da06f5a1a8999c41bab0181f48b8b
3
+ size 3375