CouchCat commited on
Commit
b698673
1 Parent(s): 08257dc

Add ner configs

Browse files
README.md ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ license: mit
4
+ tags:
5
+ - ner
6
+ widget:
7
+ - text: "These shoes from Tommy Hilfiger fit quite well sincerely, Oscar"
8
+ ---
9
+
10
+ ### Description
11
+
12
+ A Named Entity Recognition model trained on a customer feedback data using DistilBert.
13
+ Possible labels are in BIO-notation:
14
+
15
+ - PROD: for certain products
16
+ - BRND: for brands
17
+ - PERS: people names
18
+
19
+ The following tags are simply in place to help better categorize the previous tags
20
+
21
+ - MATR: relating to materials, e.g. cloth, leather, seam, etc.
22
+ - TIME: time related entities
23
+ - MISC: any other entities that might skew ther results
24
+
25
+ ### Usage
26
+
27
+ ```
28
+ from transformers import AutoTokenizer, AutoModelForTokenClassification
29
+
30
+ tokenizer = AutoTokenizer.from_pretrained("CouchCat/ma_ner_v7_distil")
31
+
32
+ model = AutoModelForTokenClassification.from_pretrained("CouchCat/ma_ner_v7_distil")
33
+ ```
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "B-BRND",
13
+ "1": "B-MATR",
14
+ "2": "B-MISC",
15
+ "3": "B-PERS",
16
+ "4": "B-PROD",
17
+ "5": "B-TIME",
18
+ "6": "I-BRND",
19
+ "7": "I-PERS",
20
+ "8": "O",
21
+ "9": "PAD"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "B-BRND": 0,
26
+ "B-MATR": 1,
27
+ "B-MISC": 2,
28
+ "B-PERS": 3,
29
+ "B-PROD": 4,
30
+ "B-TIME": 5,
31
+ "I-BRND": 6,
32
+ "I-PERS": 7,
33
+ "O": 8,
34
+ "PAD": 9
35
+ },
36
+ "max_position_embeddings": 512,
37
+ "model_type": "distilbert",
38
+ "n_heads": 12,
39
+ "n_layers": 6,
40
+ "output_past": true,
41
+ "pad_token_id": 0,
42
+ "qa_dropout": 0.1,
43
+ "seq_classif_dropout": 0.2,
44
+ "sinusoidal_pos_embds": false,
45
+ "tie_weights_": true,
46
+ "transformers_version": "4.3.2",
47
+ "vocab_size": 28996
48
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ea11f5b2435ac079502bf2080ff6eef7d69b4e9d2f35a94eddb7c2c5b02f12
3
+ size 260835627
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "distilbert-base-cased"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff