Hugging Face's logo

dwzhu
/
e5rope-base

Sentence Similarity
sentence-transformers
Safetensors
English
e5rope
mteb
Sentence Transformers
custom_code
Inference Endpoints
Model card Files Community
1
dwzhu commited on
Commit
cd87170
•
1 Parent(s): f5ef78e

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +34 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +44 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +62 -0
  6. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dwzhu/e5rope-base",
3
+ "architectures": [
4
+ "E5RopeModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "auto_map": {
8
+ "AutoConfig": "dwzhu/e5rope-base--configuration_e5rope.E5RopeConfig",
9
+ "AutoModel": "dwzhu/e5rope-base--modeling_e5rope.E5RopeModel"
10
+ },
11
+ "classifier_dropout": null,
12
+ "embedding_size": 768,
13
+ "gradient_checkpointing": false,
14
+ "hidden_act": "gelu",
15
+ "hidden_dropout_prob": 0.1,
16
+ "hidden_size": 768,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "e5rope",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 0,
25
+ "pose_target_len": null,
26
+ "rope_theta": 10000,
27
+ "rotary_value": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.38.2",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "use_pose": false,
33
+ "vocab_size": 30522
34
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2cd15246587918ddd3cd9ffdf55088cf2cd5c445c31a325c55706bf5803e8b
3
+ size 434015800
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[PAD]",
4
+ "[UNK]",
5
+ "[CLS]",
6
+ "[SEP]",
7
+ "[MASK]"
8
+ ],
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "[MASK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "[PAD]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "[SEP]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "[UNK]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [
45
+ "[PAD]",
46
+ "[UNK]",
47
+ "[CLS]",
48
+ "[SEP]",
49
+ "[MASK]"
50
+ ],
51
+ "clean_up_tokenization_spaces": true,
52
+ "cls_token": "[CLS]",
53
+ "do_lower_case": true,
54
+ "mask_token": "[MASK]",
55
+ "model_max_length": 512,
56
+ "pad_token": "[PAD]",
57
+ "sep_token": "[SEP]",
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "unk_token": "[UNK]"
62
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff