evangeliazve commited on
Commit
763ede4
1 Parent(s): 46b78c1

evangeliazve/articles-ner-camembert-v2

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "camembert-base",
3
+ "architectures": [
4
+ "CamembertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 5,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 6,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "-100": "IGN",
15
+ "0": "B-JOB",
16
+ "1": "I-JOB",
17
+ "2": "B-ORG",
18
+ "3": "I-ORG",
19
+ "4": "B-PER",
20
+ "5": "I-PER",
21
+ "6": "O"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "B-JOB": 0,
27
+ "B-ORG": 2,
28
+ "B-PER": 4,
29
+ "I-JOB": 1,
30
+ "I-ORG": 3,
31
+ "I-PER": 5,
32
+ "O": 6
33
+ },
34
+ "layer_norm_eps": 1e-05,
35
+ "max_position_embeddings": 514,
36
+ "model_type": "camembert",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 12,
39
+ "output_past": true,
40
+ "pad_token_id": 1,
41
+ "position_embedding_type": "absolute",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.24.0",
44
+ "type_vocab_size": 1,
45
+ "use_cache": true,
46
+ "vocab_size": 32005
47
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe39bcf038164d05ba71cfdbc7a4e1b7dc882424fe74114ec4ced5dc903250e9
3
+ size 440220013
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "unk_token": "<unk>"
19
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "ignore_mismatched_sizes": true,
10
+ "mask_token": {
11
+ "__type": "AddedToken",
12
+ "content": "<mask>",
13
+ "lstrip": true,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "model_max_length": 512,
19
+ "name_or_path": "camembert-base",
20
+ "pad_token": "<pad>",
21
+ "sep_token": "</s>",
22
+ "special_tokens_map_file": null,
23
+ "tokenizer_class": "CamembertTokenizer",
24
+ "unk_token": "<unk>"
25
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c0909bd88834107162c4ebb2ad8d677317f69664c4f2db9d31aa8c3de49eb3
3
+ size 3451