CouchCat commited on
Commit
398fea3
1 Parent(s): 4daf89c

Add NER configs

Browse files
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForTokenClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "BRND",
12
+ "1": "O",
13
+ "2": "PAD",
14
+ "3": "PRD"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "BRND": 0,
19
+ "O": 1,
20
+ "PAD": 2,
21
+ "PRD": 3
22
+ },
23
+ "max_position_embeddings": 512,
24
+ "model_type": "distilbert",
25
+ "n_heads": 12,
26
+ "n_layers": 6,
27
+ "output_past": true,
28
+ "pad_token_id": 0,
29
+ "qa_dropout": 0.1,
30
+ "seq_classif_dropout": 0.2,
31
+ "sinusoidal_pos_embds": false,
32
+ "tie_weights_": true,
33
+ "vocab_size": 28996
34
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1938b801b1c8e46b96fd20b7ed31561caf1c883675ec51fba7100e7888ae646b
3
+ size 260817195
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, "model_max_length": 512}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff