nhanv commited on
Commit
83dbc58
1 Parent(s): 9df65fd

init project

Browse files
README.md CHANGED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: ner-vietnamese-electra-base
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # cv-ner
13
+
14
+ This model is a fine-tuned version of [/datahdd/nhanv/git/nlp_toolkit/outputs/cv-ner](https://huggingface.co//datahdd/nhanv/git/nlp_toolkit/outputs/cv-ner) on an unknown dataset.
15
+
16
+ ## Model description
17
+
18
+ More information needed
19
+
20
+ ## Intended uses & limitations
21
+
22
+ More information needed
23
+
24
+ ## Training and evaluation data
25
+
26
+ More information needed
27
+
28
+ ## Training procedure
29
+
30
+ ### Training hyperparameters
31
+
32
+ The following hyperparameters were used during training:
33
+ - learning_rate: 5e-05
34
+ - train_batch_size: 16
35
+ - eval_batch_size: 4
36
+ - seed: 42
37
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
38
+ - lr_scheduler_type: linear
39
+ - num_epochs: 10.0
40
+
41
+ ### Framework versions
42
+
43
+ - Transformers 4.20.1
44
+ - Pytorch 1.8.0+cu111
45
+ - Datasets 2.4.0
46
+ - Tokenizers 0.12.1
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NlpHUST/electra-base-vn",
3
+ "architectures": [
4
+ "ElectraForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "finetuning_task": "ner",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "B-LOCATION",
15
+ "1": "B-MISCELLANEOUS",
16
+ "2": "B-ORGANIZATION",
17
+ "3": "B-PERSON",
18
+ "4": "I-LOCATION",
19
+ "5": "I-MISCELLANEOUS",
20
+ "6": "I-ORGANIZATION",
21
+ "7": "I-PERSON",
22
+ "8": "O"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "B-LOCATION": 0,
28
+ "B-MISCELLANEOUS": 1,
29
+ "B-ORGANIZATION": 2,
30
+ "B-PERSON": 3,
31
+ "I-LOCATION": 4,
32
+ "I-MISCELLANEOUS": 5,
33
+ "I-ORGANIZATION": 6,
34
+ "I-PERSON": 7,
35
+ "O": 8
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "electra",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "position_embedding_type": "absolute",
44
+ "summary_activation": "gelu",
45
+ "summary_last_dropout": 0.1,
46
+ "summary_type": "first",
47
+ "summary_use_proj": true,
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.22.2",
50
+ "type_vocab_size": 2,
51
+ "use_cache": true,
52
+ "vocab_size": 62000
53
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88bc614905a1f337a3b97190636dff75420d66b6b71a76c382ea5cfa8e0a381e
3
+ size 532365681
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "name_or_path": "NlpHUST/electra-base-vn",
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "ElectraTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff