Hugging Face's logo

anondeb
/
arabertv02_reranker_2021

Safetensors
bert
Model card Files Community
anondeb commited on
Commit
ac5df80
·
verified ·
1 Parent(s): 41f9663

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +11 -10
  2. model.safetensors +3 -0
  3. special_tokens_map.json +37 -1
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +87 -1
  6. vocab.txt +0 -0
config.json CHANGED
@@ -1,15 +1,23 @@
1
  {
 
2
  "architectures": [
3
  "BertForSequenceClassification"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
 
6
  "directionality": "bidi",
7
  "gradient_checkpointing": false,
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 768,
 
 
 
11
  "initializer_range": 0.02,
12
  "intermediate_size": 3072,
 
 
 
13
  "layer_norm_eps": 1e-12,
14
  "max_position_embeddings": 512,
15
  "model_type": "bert",
@@ -22,16 +30,9 @@
22
  "pooler_size_per_head": 128,
23
  "pooler_type": "first_token_transform",
24
  "position_embedding_type": "absolute",
25
- "transformers_version": "4.3.0",
 
26
  "type_vocab_size": 2,
27
  "use_cache": true,
28
- "vocab_size": 64000,
29
- "id2label": {
30
- "0": "NOT_SIMILAR",
31
- "1": "SIMILAR"
32
- },
33
- "label2id": {
34
- "NOT_SIMILAR": 0,
35
- "SIMILAR": 1
36
- }
37
  }
 
1
  {
2
+ "_name_or_path": "/mnt/f/old_repos/dalil_triton_inference_micro_service/orig_models/ranker_arabertv02_armsmarco/",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
  "directionality": "bidi",
9
  "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
  "initializer_range": 0.02,
17
  "intermediate_size": 3072,
18
+ "label2id": {
19
+ "0": "LABEL_0"
20
+ },
21
  "layer_norm_eps": 1e-12,
22
  "max_position_embeddings": 512,
23
  "model_type": "bert",
 
30
  "pooler_size_per_head": 128,
31
  "pooler_type": "first_token_transform",
32
  "position_embedding_type": "absolute",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.48.3",
35
  "type_vocab_size": 2,
36
  "use_cache": true,
37
+ "vocab_size": 64000
 
 
 
 
 
 
 
 
38
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:516f254a957b41bd90c66c5483a9f3dfbd9ad2af816c2a8e47d8813cbfcea632
3
+ size 540799996
special_tokens_map.json CHANGED
@@ -1 +1,37 @@
1
- {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1,87 @@
1
- {"do_lower_case": false, "max_len": 512, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": ["[بريد]", "[مستخدم]", "[رابط]"], "special_tokens_map_file": null, "name_or_path": "aubmindlab/bert-base-arabertv02"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[رابط]",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": true,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[بريد]",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": true,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "[مستخدم]",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": true,
65
+ "special": true
66
+ }
67
+ },
68
+ "clean_up_tokenization_spaces": false,
69
+ "cls_token": "[CLS]",
70
+ "do_basic_tokenize": true,
71
+ "do_lower_case": false,
72
+ "extra_special_tokens": {},
73
+ "mask_token": "[MASK]",
74
+ "max_len": 512,
75
+ "model_max_length": 512,
76
+ "never_split": [
77
+ "[بريد]",
78
+ "[مستخدم]",
79
+ "[رابط]"
80
+ ],
81
+ "pad_token": "[PAD]",
82
+ "sep_token": "[SEP]",
83
+ "strip_accents": null,
84
+ "tokenize_chinese_chars": true,
85
+ "tokenizer_class": "BertTokenizer",
86
+ "unk_token": "[UNK]"
87
+ }
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff