Hugging Face's logo

Todai
/
robbert-2022-dutch-sentence-transformers-onnx

Sentence Similarity
sentence-transformers
ONNX
Transformers.js
Dutch
roberta
feature-extraction
feature_extraction
text-embeddings-inference
Inference Endpoints
Model card Files Community
Todai commited on
Commit
96b78d6
•
1 Parent(s): f9541ca

Upload 11 files

Browse files
Files changed (11) hide show
  1. config.json +28 -0
  2. merges.txt +0 -0
  3. model.onnx +3 -0
  4. model_quantized.onnx +3 -0
  5. onnx/model.onnx +3 -0
  6. onnx/model_quantized.onnx +3 -0
  7. quantize_config.json +36 -0
  8. special_tokens_map.json +15 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +71 -0
  11. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NetherlandsForensicInstitute/robbert-2022-dutch-sentence-transformers",
3
+ "architectures": [
4
+ "RobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "transformers_version": "4.33.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 42774
28
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:427f8a29b6c9c51106d5c6f65e533182018747ff7b1be59270c59f06abe0c05e
3
+ size 473454667
model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dda96e1bd53dbfc6c7a25a70f015f2a4ba04c1d1f4a10f20162203a7e07d9ee7
3
+ size 119496558
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:427f8a29b6c9c51106d5c6f65e533182018747ff7b1be59270c59f06abe0c05e
3
+ size 473454667
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dda96e1bd53dbfc6c7a25a70f015f2a4ba04c1d1f4a10f20162203a7e07d9ee7
3
+ size 119496558
quantize_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Unsqueeze",
8
+ "Add",
9
+ "Not",
10
+ "Slice",
11
+ "Constant",
12
+ "ConstantOfShape",
13
+ "Div",
14
+ "Pow",
15
+ "Concat",
16
+ "ReduceMean",
17
+ "CumSum",
18
+ "Sqrt",
19
+ "Mul",
20
+ "Shape",
21
+ "Reshape",
22
+ "Transpose",
23
+ "Where",
24
+ "Cast",
25
+ "Gather",
26
+ "Erf",
27
+ "Sub",
28
+ "Expand",
29
+ "Equal",
30
+ "Softmax",
31
+ "MatMul"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ }
35
+ }
36
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "max_length": 128,
38
+ "model_max_length": 512,
39
+ "pad_to_multiple_of": null,
40
+ "pad_token": {
41
+ "__type": "AddedToken",
42
+ "content": "<pad>",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "pad_token_type_id": 0,
49
+ "padding_side": "right",
50
+ "sep_token": {
51
+ "__type": "AddedToken",
52
+ "content": "</s>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false
57
+ },
58
+ "stride": 0,
59
+ "tokenizer_class": "RobertaTokenizer",
60
+ "trim_offsets": true,
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": {
64
+ "__type": "AddedToken",
65
+ "content": "<unk>",
66
+ "lstrip": false,
67
+ "normalized": true,
68
+ "rstrip": false,
69
+ "single_word": false
70
+ }
71
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff