jdp8 commited on
Commit
cb68031
1 Parent(s): dcc6004

Initial commit

Browse files
README.md ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ https://huggingface.co/Babelscape/wikineural-multilingual-ner with ONNX weights to be compatible with Transformers.js.
2
+
3
+ Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Babelscape/wikineural-multilingual-ner",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-PER",
15
+ "2": "I-PER",
16
+ "3": "B-ORG",
17
+ "4": "I-ORG",
18
+ "5": "B-LOC",
19
+ "6": "I-LOC",
20
+ "7": "B-MISC",
21
+ "8": "I-MISC"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "B-LOC": 5,
27
+ "B-MISC": 7,
28
+ "B-ORG": 3,
29
+ "B-PER": 1,
30
+ "I-LOC": 6,
31
+ "I-MISC": 8,
32
+ "I-ORG": 4,
33
+ "I-PER": 2,
34
+ "O": 0
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "pooler_fc_size": 768,
43
+ "pooler_num_attention_heads": 12,
44
+ "pooler_num_fc_layers": 3,
45
+ "pooler_size_per_head": 128,
46
+ "pooler_type": "first_token_transform",
47
+ "position_embedding_type": "absolute",
48
+ "transformers_version": "4.33.2",
49
+ "type_vocab_size": 2,
50
+ "use_cache": true,
51
+ "vocab_size": 119547
52
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2cadc4d49eaa7d938428cd3641c22c23b80d647f1eda2d547b4bee1583eb4e
3
+ size 709345295
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90a16d04fa98123cb49ba65c69892b963259700889589d00bef18971be4f0b16
3
+ size 178495474
quantize_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "model": {
6
+ "op_types": [
7
+ "Slice",
8
+ "Unsqueeze",
9
+ "Div",
10
+ "Sub",
11
+ "Erf",
12
+ "Softmax",
13
+ "Gather",
14
+ "Sqrt",
15
+ "ReduceMean",
16
+ "MatMul",
17
+ "Transpose",
18
+ "Constant",
19
+ "Add",
20
+ "Pow",
21
+ "Concat",
22
+ "Reshape",
23
+ "Cast",
24
+ "Shape",
25
+ "Mul"
26
+ ],
27
+ "weight_type": "QInt8"
28
+ }
29
+ }
30
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "max_length": 512,
7
+ "model_max_length": 512,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "stride": 0,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "truncation_side": "right",
15
+ "truncation_strategy": "longest_first",
16
+ "unk_token": "[UNK]"
17
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff