Hugging Face's logo

jinaai
/
jina-bert-flash-implementation

Transformers
bert
custom_code
Inference Endpoints
🇪🇺 Region: EU
Model card Files Community
18
koukandre commited on
Commit
6c468c3
•
1 Parent(s): 71aae6d

Add model configs and tokenizer files

Browse files
Files changed (5) hide show
  1. config.json +40 -0
  2. special_tokens_map.json +37 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +57 -0
  5. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jinaai/jina-bert-flash-implementation",
3
+ "auto_map": {
4
+ "AutoConfig": "jinaai/jina-bert-flash-implementation--configuration_bert.JinaBertConfig",
5
+ "AutoModel": "jinaai/jina-bert-flash-implementation--modeling_bert.BertModel",
6
+ "AutoModelForPreTraining": "jinaai/jina-bert-flash-implementation--modeling_bert.BertForPreTraining",
7
+ "AutoModelForMaskedLM": "jinaai/jina-bert-flash-implementation--modeling_bert.BertForPreTraining"
8
+ },
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "classifier_dropout": null,
11
+ "dense_seq_output": false,
12
+ "emb_pooler": null,
13
+ "fused_bias_fc": false,
14
+ "fused_dropout_add_ln": false,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.1,
17
+ "hidden_size": 768,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "last_layer_subset": false,
21
+ "layer_norm_eps": 1e-12,
22
+ "mlp_checkpoint_lvl": 0,
23
+ "mlp_type": "glu",
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "num_loras": 5,
28
+ "pad_token_id": 0,
29
+ "pad_vocab_size_multiple": 1,
30
+ "torch_dtype": "float16",
31
+ "transformers_version": "4.39.3",
32
+ "type_vocab_size": 2,
33
+ "use_flash_attn": true,
34
+ "use_qk_norm": false,
35
+ "vocab_size": 30528,
36
+ "window_size": [
37
+ -1,
38
+ -1
39
+ ]
40
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 8192,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff