taegyeonglee commited on
Commit
110e891
·
verified ·
1 Parent(s): c62ec7b

Repackaged LQ-KBERT-Base into Hugging Face standard format

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/bert-base",
3
+ "architectures": [
4
+ "KbertMTL"
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
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "langquant_info": {
14
+ "base_model": "klue/bert-base",
15
+ "head_structure": {
16
+ "action": 6,
17
+ "emotion": 7,
18
+ "regression": 3,
19
+ "sentiment": 5
20
+ },
21
+ "license": "cc-by-nc-4.0",
22
+ "model_name": "LQ-KBERT-Base",
23
+ "organization": "LangQuant",
24
+ "source_ckpt": "lq-kbert-base.pt",
25
+ "task": "Crypto Market Korean Sentiment & Action Signal Classification",
26
+ "year": 2025
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "max_position_embeddings": 512,
30
+ "model_type": "bert",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 0,
34
+ "position_embedding_type": "absolute",
35
+ "transformers_version": "4.27.0",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 32000
39
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c866cfae6b4c43cfc668909f775b91a1da962f283f3cdd589f56e7f44bef9b5
3
+ size 442620643
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
+ "model_max_length": 512,
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": "C:\\Users\\user/.cache\\huggingface\\hub\\models--klue--bert-base\\snapshots\\77c8b3d707df785034b4e50f2da5d37be5f0f546\\special_tokens_map.json",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff