evangeliazve commited on
Commit
15785af
1 Parent(s): 96277e5

evangeliazve/articles-ner-mpnet

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/mpnet-base",
3
+ "architectures": [
4
+ "MPNetForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "-100": "IGN",
14
+ "0": "B-JOB",
15
+ "1": "I-JOB",
16
+ "2": "B-ORG",
17
+ "3": "I-ORG",
18
+ "4": "B-PER",
19
+ "5": "I-PER",
20
+ "6": "O"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "B-JOB": 0,
26
+ "B-ORG": 2,
27
+ "B-PER": 4,
28
+ "I-JOB": 1,
29
+ "I-ORG": 3,
30
+ "I-PER": 5,
31
+ "O": 6
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "mpnet",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "pad_token_id": 1,
39
+ "relative_attention_num_buckets": 32,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.24.0",
42
+ "vocab_size": 30527
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db1e14ab8fdc935ba9d6412a47bb25bb700a3e7990b928dd7b1a380d83e84648
3
+ size 435674029
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "do_lower_case": true,
5
+ "eos_token": "</s>",
6
+ "ignore_mismatched_sizes": true,
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "microsoft/mpnet-base",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "strip_accents": null,
14
+ "tokenize_chinese_chars": true,
15
+ "tokenizer_class": "MPNetTokenizer",
16
+ "unk_token": "[UNK]"
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:302b7ff7da359e045d177e065611bd01b05457fc52d3047a195413c037e47c3f
3
+ size 3451
vocab.txt ADDED
The diff for this file is too large to render. See raw diff