joshdevins
commited on
Commit
•
901c3c5
1
Parent(s):
c754d80
First commit of NER fine-tuning DistilBERT cased
Browse files- config.json +47 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"finetuning_task": "ner",
|
11 |
+
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6",
|
20 |
+
"7": "LABEL_7",
|
21 |
+
"8": "LABEL_8"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"label2id": {
|
25 |
+
"LABEL_0": 0,
|
26 |
+
"LABEL_1": 1,
|
27 |
+
"LABEL_2": 2,
|
28 |
+
"LABEL_3": 3,
|
29 |
+
"LABEL_4": 4,
|
30 |
+
"LABEL_5": 5,
|
31 |
+
"LABEL_6": 6,
|
32 |
+
"LABEL_7": 7,
|
33 |
+
"LABEL_8": 8
|
34 |
+
},
|
35 |
+
"max_position_embeddings": 512,
|
36 |
+
"model_type": "distilbert",
|
37 |
+
"n_heads": 12,
|
38 |
+
"n_layers": 6,
|
39 |
+
"output_past": true,
|
40 |
+
"pad_token_id": 0,
|
41 |
+
"qa_dropout": 0.1,
|
42 |
+
"seq_classif_dropout": 0.2,
|
43 |
+
"sinusoidal_pos_embds": false,
|
44 |
+
"tie_weights_": true,
|
45 |
+
"transformers_version": "4.3.1",
|
46 |
+
"vocab_size": 28996
|
47 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84e7920a9300b9bc91267fd9842eb15211b9e683a5adf1d61fc966e0c8c9e928
|
3 |
+
size 260832555
|
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, "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
|
|