Hugging Face's logo

Alibaba-NLP
/
gte-en-mlm-base

Fill-Mask
Safetensors
English
new
custom_code
Model card Files Community
izhx commited on
Commit
ff3b9c0
•
1 Parent(s): a6fb94c

Upload model

Browse files
Files changed (5) hide show
  1. config.json +38 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +37 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +55 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "NewForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "auto_map": {
7
+ "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
8
+ "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
9
+ "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
10
+ "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
11
+ "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
12
+ "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
13
+ "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
14
+ },
15
+ "classifier_dropout": 0.1,
16
+ "hidden_act": "gelu",
17
+ "hidden_dropout_prob": 0.1,
18
+ "hidden_size": 768,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "layer_norm_eps": 1e-12,
22
+ "layer_norm_type": "layer_norm",
23
+ "max_position_embeddings": 8192,
24
+ "model_type": "new",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pack_qkv": true,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "rope",
30
+ "rope_scaling": null,
31
+ "rope_theta": 500000,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.37.2",
34
+ "type_vocab_size": 0,
35
+ "unpad_inputs": false,
36
+ "use_memory_efficient_attention": false,
37
+ "vocab_size": 30528
38
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88b52a045f84a123fe7dbac264bea14bd91ff9e8a742a1429bd3f63cb304cb87
3
+ size 549610728
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 32768,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }