Hugging Face's logo

Xenova
/
GIST-small-Embedding-v0

Feature Extraction
Transformers.js
ONNX
bert
Model card Files
xet
Community
1
Xenova HF Staff commited on
Commit
7aa2a74
·
verified ·
1 Parent(s): f2ed645

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. config.json +30 -0
  2. onnx/model.onnx +3 -0
  3. onnx/model_bnb4.onnx +3 -0
  4. onnx/model_fp16.onnx +3 -0
  5. onnx/model_int8.onnx +3 -0
  6. onnx/model_q4.onnx +3 -0
  7. onnx/model_quantized.onnx +3 -0
  8. onnx/model_uint8.onnx +3 -0
  9. quantize_config.json +102 -0
  10. special_tokens_map.json +37 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +57 -0
  13. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "avsolatorio/GIST-small-Embedding-v0",
3
+ "architectures": [
4
+ "BertModel"
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": 384,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 1536,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "bert",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 0,
25
+ "position_embedding_type": "absolute",
26
+ "transformers_version": "4.38.2",
27
+ "type_vocab_size": 2,
28
+ "use_cache": true,
29
+ "vocab_size": 30522
30
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c95502dc23d4ffb50a81d3838f721abde71509982d720d355ce52c0cdfe2dfe
3
+ size 133093492
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8feaefe7234eef30393251982be01073261d775cbc3f5a4ed575a9e7737840b3
3
+ size 60113951
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f32e5697a3f9a07ff76cc3022a113c5b8eea16a163974aa52f62c8ec0bc9c900
3
+ size 66749214
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a66dc765b3c1478fed4fcf6305007aeb261c350b7761f934e734b35e905511d
3
+ size 34015110
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8381822eb018e5ba1efb5c10848369c0fd658c6ea1fe984d4312ab2dae8d83e8
3
+ size 61440599
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a66dc765b3c1478fed4fcf6305007aeb261c350b7761f934e734b35e905511d
3
+ size 34015110
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b73dda54c8b3afc10eee7b8b0c2be19ecc87a96753b32cc83ee439b5fc5b36
3
+ size 34015108
quantize_config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fp16": {},
3
+ "q8": {
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Add",
8
+ "Cast",
9
+ "Concat",
10
+ "Constant",
11
+ "Div",
12
+ "Erf",
13
+ "Gather",
14
+ "MatMul",
15
+ "Mul",
16
+ "Pow",
17
+ "ReduceMean",
18
+ "Reshape",
19
+ "Shape",
20
+ "Slice",
21
+ "Softmax",
22
+ "Sqrt",
23
+ "Sub",
24
+ "Transpose",
25
+ "Unsqueeze"
26
+ ],
27
+ "weight_type": "QInt8"
28
+ }
29
+ },
30
+ "per_channel": true,
31
+ "reduce_range": true
32
+ },
33
+ "int8": {
34
+ "per_model_config": {
35
+ "model": {
36
+ "op_types": [
37
+ "Add",
38
+ "Cast",
39
+ "Concat",
40
+ "Constant",
41
+ "Div",
42
+ "Erf",
43
+ "Gather",
44
+ "MatMul",
45
+ "Mul",
46
+ "Pow",
47
+ "ReduceMean",
48
+ "Reshape",
49
+ "Shape",
50
+ "Slice",
51
+ "Softmax",
52
+ "Sqrt",
53
+ "Sub",
54
+ "Transpose",
55
+ "Unsqueeze"
56
+ ],
57
+ "weight_type": "QInt8"
58
+ }
59
+ },
60
+ "per_channel": true,
61
+ "reduce_range": true
62
+ },
63
+ "uint8": {
64
+ "per_model_config": {
65
+ "model": {
66
+ "op_types": [
67
+ "Add",
68
+ "Cast",
69
+ "Concat",
70
+ "Constant",
71
+ "Div",
72
+ "Erf",
73
+ "Gather",
74
+ "MatMul",
75
+ "Mul",
76
+ "Pow",
77
+ "ReduceMean",
78
+ "Reshape",
79
+ "Shape",
80
+ "Slice",
81
+ "Softmax",
82
+ "Sqrt",
83
+ "Sub",
84
+ "Transpose",
85
+ "Unsqueeze"
86
+ ],
87
+ "weight_type": "QUInt8"
88
+ }
89
+ },
90
+ "per_channel": true,
91
+ "reduce_range": true
92
+ },
93
+ "q4": {
94
+ "block_size": 32,
95
+ "is_symmetric": true,
96
+ "accuracy_level": null
97
+ },
98
+ "bnb4": {
99
+ "block_size": 64,
100
+ "quant_type": 1
101
+ }
102
+ }
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": 512,
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