Hugging Face's logo

Xenova
/
text2vec-base-chinese-sentence

Feature Extraction
Transformers.js
ONNX
ernie
Model card Files Community
Xenova HF staff commited on
Commit
9c976b2
•
1 Parent(s): 61bfa6f

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. added_tokens.json +3 -0
  2. config.json +26 -0
  3. onnx/model.onnx +3 -0
  4. onnx/model_bnb4.onnx +3 -0
  5. onnx/model_fp16.onnx +3 -0
  6. onnx/model_int8.onnx +3 -0
  7. onnx/model_q4.onnx +3 -0
  8. onnx/model_quantized.onnx +3 -0
  9. onnx/model_uint8.onnx +3 -0
  10. quantize_config.json +105 -0
  11. special_tokens_map.json +37 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +64 -0
  14. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[UNK]": 39979
3
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "shibing624/text2vec-base-chinese-sentence",
3
+ "architectures": [
4
+ "ErnieModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
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-05,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "ernie",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "task_type_vocab_size": 3,
21
+ "transformers_version": "4.38.2",
22
+ "type_vocab_size": 4,
23
+ "use_cache": true,
24
+ "use_task_id": true,
25
+ "vocab_size": 40000
26
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5110fbccaa2c9621b752af8cadeffa383f87771f7d13c1b4e4ba377cd893bed2
3
+ size 469675392
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:351a2f844eb93ed6aade98f2df01ab77788ea08413b23e11343071f957356437
3
+ size 177723714
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc07c878c1698ee530d4767dc9d3834fe567b1038b7c79b5a78da77d1ad451e
3
+ size 235047392
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b377b97fd0dbb293a2730a7a3cba6a969b0a0787e6d66a37a5a41596dc35db
3
+ size 118561022
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee458d769dc4fa7ea6a2c7b90e48944dc828e00af4c151ceb041769362c824fe
3
+ size 183031602
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b377b97fd0dbb293a2730a7a3cba6a969b0a0787e6d66a37a5a41596dc35db
3
+ size 118561022
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e8a59f8c85d13195fb226e03d42e68671a2562ad67236d3c7443a681beca67
3
+ size 118561020
quantize_config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fp16": {},
3
+ "q8": {
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Add",
8
+ "Cast",
9
+ "Concat",
10
+ "Constant",
11
+ "ConstantOfShape",
12
+ "Div",
13
+ "Erf",
14
+ "Gather",
15
+ "MatMul",
16
+ "Mul",
17
+ "Pow",
18
+ "ReduceMean",
19
+ "Reshape",
20
+ "Shape",
21
+ "Slice",
22
+ "Softmax",
23
+ "Sqrt",
24
+ "Sub",
25
+ "Transpose",
26
+ "Unsqueeze"
27
+ ],
28
+ "weight_type": "QInt8"
29
+ }
30
+ },
31
+ "per_channel": true,
32
+ "reduce_range": true
33
+ },
34
+ "int8": {
35
+ "per_model_config": {
36
+ "model": {
37
+ "op_types": [
38
+ "Add",
39
+ "Cast",
40
+ "Concat",
41
+ "Constant",
42
+ "ConstantOfShape",
43
+ "Div",
44
+ "Erf",
45
+ "Gather",
46
+ "MatMul",
47
+ "Mul",
48
+ "Pow",
49
+ "ReduceMean",
50
+ "Reshape",
51
+ "Shape",
52
+ "Slice",
53
+ "Softmax",
54
+ "Sqrt",
55
+ "Sub",
56
+ "Transpose",
57
+ "Unsqueeze"
58
+ ],
59
+ "weight_type": "QInt8"
60
+ }
61
+ },
62
+ "per_channel": true,
63
+ "reduce_range": true
64
+ },
65
+ "uint8": {
66
+ "per_model_config": {
67
+ "model": {
68
+ "op_types": [
69
+ "Add",
70
+ "Cast",
71
+ "Concat",
72
+ "Constant",
73
+ "ConstantOfShape",
74
+ "Div",
75
+ "Erf",
76
+ "Gather",
77
+ "MatMul",
78
+ "Mul",
79
+ "Pow",
80
+ "ReduceMean",
81
+ "Reshape",
82
+ "Shape",
83
+ "Slice",
84
+ "Softmax",
85
+ "Sqrt",
86
+ "Sub",
87
+ "Transpose",
88
+ "Unsqueeze"
89
+ ],
90
+ "weight_type": "QUInt8"
91
+ }
92
+ },
93
+ "per_channel": true,
94
+ "reduce_range": true
95
+ },
96
+ "q4": {
97
+ "block_size": 32,
98
+ "is_symmetric": true,
99
+ "accuracy_level": null
100
+ },
101
+ "bnb4": {
102
+ "block_size": 64,
103
+ "quant_type": 1
104
+ }
105
+ }
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 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[MASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "39979": {
36
+ "content": "[UNK]",
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
+ "max_length": 256,
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff