Hugging Face's logo

keras
/
bge_large_zh

KerasHub
Model card Files
xet
 Community
laxmareddyp commited on
Commit
c81d08f
·
verified ·
1 Parent(s): 3ec70ef

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. README.md +20 -0
  2. assets/tokenizer/vocabulary.txt +0 -0
  3. config.json +25 -0
  4. metadata.json +11 -0
  5. model.weights.h5 +3 -0
  6. preprocessor.json +47 -0
  7. task.json +82 -0
  8. tokenizer.json +27 -0
README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: keras-hub
3
+ ---
4
+ This is a [`Bert` model](https://keras.io/api/keras_hub/models/bert) uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
5
+ This model is related to a `TextEmbedder` task.
6
+
7
+ Model config:
8
+ * **name:** bert_backbone
9
+ * **trainable:** True
10
+ * **dtype:** {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}
11
+ * **vocabulary_size:** 21128
12
+ * **num_layers:** 24
13
+ * **num_heads:** 16
14
+ * **hidden_dim:** 1024
15
+ * **intermediate_dim:** 4096
16
+ * **dropout:** 0.1
17
+ * **max_sequence_length:** 512
18
+ * **num_segments:** 2
19
+
20
+ This model card has been generated automatically and should be completed by the model author. See [Model Cards documentation](https://huggingface.co/docs/hub/model-cards) for more information.
assets/tokenizer/vocabulary.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "module": "keras_hub.src.models.bert.bert_backbone",
3
+ "class_name": "BertBackbone",
4
+ "config": {
5
+ "name": "bert_backbone",
6
+ "trainable": true,
7
+ "dtype": {
8
+ "module": "keras",
9
+ "class_name": "DTypePolicy",
10
+ "config": {
11
+ "name": "float32"
12
+ },
13
+ "registered_name": null
14
+ },
15
+ "vocabulary_size": 21128,
16
+ "num_layers": 24,
17
+ "num_heads": 16,
18
+ "hidden_dim": 1024,
19
+ "intermediate_dim": 4096,
20
+ "dropout": 0.1,
21
+ "max_sequence_length": 512,
22
+ "num_segments": 2
23
+ },
24
+ "registered_name": "keras_hub>BertBackbone"
25
+ }
metadata.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "keras_version": "3.13.2",
3
+ "keras_hub_version": "0.30.0.dev0",
4
+ "parameter_count": 325522432,
5
+ "date_saved": "2026-07-04@10:24:46",
6
+ "tasks": [
7
+ "MaskedLM",
8
+ "TextClassifier",
9
+ "TextEmbedder"
10
+ ]
11
+ }
model.weights.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c323641db0400d50e60acd0218ee0ba0f0d069dfa36a9d8d38d0658d08e83448
3
+ size 1302928688
preprocessor.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "module": "keras_hub.src.models.bert.bert_text_embedder_preprocessor",
3
+ "class_name": "BertTextEmbedderPreprocessor",
4
+ "config": {
5
+ "name": "bert_text_embedder_preprocessor",
6
+ "trainable": true,
7
+ "dtype": {
8
+ "module": "keras",
9
+ "class_name": "DTypePolicy",
10
+ "config": {
11
+ "name": "float32"
12
+ },
13
+ "registered_name": null
14
+ },
15
+ "tokenizer": {
16
+ "module": "keras_hub.src.models.bert.bert_tokenizer",
17
+ "class_name": "BertTokenizer",
18
+ "config": {
19
+ "name": "bert_tokenizer",
20
+ "trainable": true,
21
+ "dtype": {
22
+ "module": "keras",
23
+ "class_name": "DTypePolicy",
24
+ "config": {
25
+ "name": "int32"
26
+ },
27
+ "registered_name": null
28
+ },
29
+ "config_file": "tokenizer.json",
30
+ "vocabulary": null,
31
+ "sequence_length": null,
32
+ "lowercase": true,
33
+ "strip_accents": false,
34
+ "split": true,
35
+ "suffix_indicator": "##",
36
+ "oov_token": "[UNK]",
37
+ "special_tokens": null,
38
+ "special_tokens_in_strings": false
39
+ },
40
+ "registered_name": "keras_hub>BertTokenizer"
41
+ },
42
+ "config_file": "preprocessor.json",
43
+ "sequence_length": 512,
44
+ "truncate": "round_robin"
45
+ },
46
+ "registered_name": "keras_hub>BertTextEmbedderPreprocessor"
47
+ }
task.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "module": "keras_hub.src.models.bert.bert_text_embedder",
3
+ "class_name": "BertTextEmbedder",
4
+ "config": {
5
+ "backbone": {
6
+ "module": "keras_hub.src.models.bert.bert_backbone",
7
+ "class_name": "BertBackbone",
8
+ "config": {
9
+ "name": "bert_backbone",
10
+ "trainable": true,
11
+ "dtype": {
12
+ "module": "keras",
13
+ "class_name": "DTypePolicy",
14
+ "config": {
15
+ "name": "float32"
16
+ },
17
+ "registered_name": null
18
+ },
19
+ "vocabulary_size": 21128,
20
+ "num_layers": 24,
21
+ "num_heads": 16,
22
+ "hidden_dim": 1024,
23
+ "intermediate_dim": 4096,
24
+ "dropout": 0.1,
25
+ "max_sequence_length": 512,
26
+ "num_segments": 2
27
+ },
28
+ "registered_name": "keras_hub>BertBackbone"
29
+ },
30
+ "preprocessor": {
31
+ "module": "keras_hub.src.models.bert.bert_text_embedder_preprocessor",
32
+ "class_name": "BertTextEmbedderPreprocessor",
33
+ "config": {
34
+ "name": "bert_text_embedder_preprocessor",
35
+ "trainable": true,
36
+ "dtype": {
37
+ "module": "keras",
38
+ "class_name": "DTypePolicy",
39
+ "config": {
40
+ "name": "float32"
41
+ },
42
+ "registered_name": null
43
+ },
44
+ "tokenizer": {
45
+ "module": "keras_hub.src.models.bert.bert_tokenizer",
46
+ "class_name": "BertTokenizer",
47
+ "config": {
48
+ "name": "bert_tokenizer",
49
+ "trainable": true,
50
+ "dtype": {
51
+ "module": "keras",
52
+ "class_name": "DTypePolicy",
53
+ "config": {
54
+ "name": "int32"
55
+ },
56
+ "registered_name": null
57
+ },
58
+ "config_file": "tokenizer.json",
59
+ "vocabulary": null,
60
+ "sequence_length": null,
61
+ "lowercase": true,
62
+ "strip_accents": false,
63
+ "split": true,
64
+ "suffix_indicator": "##",
65
+ "oov_token": "[UNK]",
66
+ "special_tokens": null,
67
+ "special_tokens_in_strings": false
68
+ },
69
+ "registered_name": "keras_hub>BertTokenizer"
70
+ },
71
+ "config_file": "preprocessor.json",
72
+ "sequence_length": 512,
73
+ "truncate": "round_robin"
74
+ },
75
+ "registered_name": "keras_hub>BertTextEmbedderPreprocessor"
76
+ },
77
+ "name": "bert_text_embedder",
78
+ "pooling_mode": "cls",
79
+ "normalize": true
80
+ },
81
+ "registered_name": "keras_hub>BertTextEmbedder"
82
+ }
tokenizer.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "module": "keras_hub.src.models.bert.bert_tokenizer",
3
+ "class_name": "BertTokenizer",
4
+ "config": {
5
+ "name": "bert_tokenizer",
6
+ "trainable": true,
7
+ "dtype": {
8
+ "module": "keras",
9
+ "class_name": "DTypePolicy",
10
+ "config": {
11
+ "name": "int32"
12
+ },
13
+ "registered_name": null
14
+ },
15
+ "config_file": "tokenizer.json",
16
+ "vocabulary": null,
17
+ "sequence_length": null,
18
+ "lowercase": true,
19
+ "strip_accents": false,
20
+ "split": true,
21
+ "suffix_indicator": "##",
22
+ "oov_token": "[UNK]",
23
+ "special_tokens": null,
24
+ "special_tokens_in_strings": false
25
+ },
26
+ "registered_name": "keras_hub>BertTokenizer"
27
+ }