ldenoue commited on
Commit
f75c099
1 Parent(s): f6a3d37

Upload 9 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "oliverguhr/fullstop-punctuation-multilang-large",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
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": 1024,
14
+ "id2label": {
15
+ "0": "0",
16
+ "1": ".",
17
+ "2": ",",
18
+ "3": "?",
19
+ "4": "-",
20
+ "5": ":"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 4096,
24
+ "label2id": {
25
+ ",": 2,
26
+ "-": 4,
27
+ ".": 1,
28
+ "0": 0,
29
+ ":": 5,
30
+ "?": 3
31
+ },
32
+ "layer_norm_eps": 1e-05,
33
+ "max_position_embeddings": 514,
34
+ "model_type": "xlm-roberta",
35
+ "num_attention_heads": 16,
36
+ "num_hidden_layers": 24,
37
+ "output_past": true,
38
+ "pad_token_id": 1,
39
+ "position_embedding_type": "absolute",
40
+ "transformers_version": "4.33.2",
41
+ "type_vocab_size": 1,
42
+ "use_cache": true,
43
+ "vocab_size": 250002
44
+ }
onnx/.DS_Store ADDED
Binary file (6.15 kB). View file
 
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b8f6e2e753f6cab28d200307dc6ac1a5b410aab3b5913125f3397396da3a93
3
+ size 617775
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc31a4ca183152a112229a50da0ce49a9e9428502b5e2037639f2b1d87937412
3
+ size 561884470
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
+ "Div",
8
+ "ConstantOfShape",
9
+ "Mul",
10
+ "Gather",
11
+ "Sqrt",
12
+ "Transpose",
13
+ "Reshape",
14
+ "Equal",
15
+ "Expand",
16
+ "Shape",
17
+ "Erf",
18
+ "Pow",
19
+ "Add",
20
+ "Cast",
21
+ "Not",
22
+ "Concat",
23
+ "ReduceMean",
24
+ "MatMul",
25
+ "Softmax",
26
+ "Slice",
27
+ "CumSum",
28
+ "Sub",
29
+ "Unsqueeze",
30
+ "Where",
31
+ "Constant"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ }
35
+ }
36
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3788bb2f349135f2ad2e2b10dff3cee7f23fab906a5fbdadf20bc963b05b4c
3
+ size 17098080
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "<mask>",
10
+ "lstrip": true,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 512,
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "strip_accent": false,
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "unk_token": "<unk>"
22
+ }