shomez commited on
Commit
aad472c
·
1 Parent(s): 2bf43d1

Add model and tokenizer

Browse files
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/conversational-entity-linking-2022/tool/bert_conv-td",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "finetuning_task": "ner",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "B-ment",
15
+ "1": "I-ment",
16
+ "2": "O"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "B-ment": 0,
22
+ "I-ment": 1,
23
+ "O": 2
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "output_past": true,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "absolute",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.18.0",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 28996
38
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa80d1a6187a05bf5696e22819657ed5cc3f18cdb1c3c1b7ac7e381b732b386
3
+ size 430957738
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, "special_tokens_map_file": "/scratch/hjoko/.jupyter/py38_hjoko/210706_MD/210706_BERT-NER/cache/e400007653a8f46a88b57ff3ae2170756b36752a45b633f6554cce43104a6987.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "/content/conversational-entity-linking-2022/tool/bert_conv-td", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff