Ubuntu commited on
Commit
056f5c1
·
1 Parent(s): faf3eea

Figured out labels issue

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./nxs62-patents-ner_SYSFORM_chembert_cased.model/",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-SYSTEMATIC",
14
+ "2": "I-SYSTEMATIC",
15
+ "3": "B-FORMULA",
16
+ "4": "I-FORMULA"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "O": 0,
22
+ "B-SYSTEMATIC": 1,
23
+ "I-SYSTEMATIC": 2,
24
+ "B-FORMULA": 3,
25
+ "I-FORMULA": 4
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.17.0",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 28996
39
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66187ef4328f3e28690de5f3f9405de39b435c129aeb43cc30f35f3a14dd8467
3
+ size 430978417
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.json ADDED
The diff for this file is too large to render. See raw diff
 
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, "max_len": 512, "special_tokens_map_file": "/home/ubuntu/.cache/huggingface/transformers/b33bcac0ad2adc633578e3be3d1c37a843f13b95ed10144e41ce8e5619799226.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "./nxs62-patents-ner_SYSFORM_chembert_cased.model/", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41195cbfc4c5ee775581fd3ca88a78cb3a55682c3276d08960806e3a0a98464a
3
+ size 2991
vocab.txt ADDED
The diff for this file is too large to render. See raw diff