HANTAEK commited on
Commit
82c5a64
1 Parent(s): 3d9a739

Upload 6 files

Browse files

# KLUE RoBERTa Large KorQuAD v1 QA - Fine-tuned

이 모델은 [CurtisJeon/klue-roberta-large-korquad_v1_qa](https://huggingface.co/CurtisJeon/klue-roberta-large-korquad_v1_qa)를 기반으로 하여 추가 데이터로 fine-tuning한 한국어 질의응답(QA) 모델입니다.

## 모델 정보

- 기본 모델: KLUE RoBERTa Large
- 태스크: 질의응답 (Question Answering)
- 언어: 한국어
- 훈련 데이터: KorQuAD v1 + [자체 데이터]

## 모델 구조

- RobertaForQuestionAnswering 아키텍처 사용 (+CNN without dropout)
- 24개의 hidden layers
- 1024 hidden size
- 16 attention heads
- 총 파라미터: 약 355M


## 사용 방법

이 모델은 Hugging Face Transformers 라이브러리를 사용하여 쉽게 로드하고 사용할 수 있습니다:

```python
from transformers import AutoModelForQuestionAnswering, AutoTokenizer

model_name = "YOUR_USERNAME/klue-roberta-large-korquad-v1-qa-finetuned"
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa1dd8a8cf65703f4772935fe76b55db37bf1c6bb6d99025546c513b18cf54dc
3
+ size 1426552802
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "eos_token": "[SEP]",
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "name_or_path": "CurtisJeon/klue-roberta-large-korquad_v1_qa",
10
+ "never_split": null,
11
+ "pad_token": "[PAD]",
12
+ "sep_token": "[SEP]",
13
+ "special_tokens_map_file": "/data/ephemeral/huggingface/models--klue--roberta-large/snapshots/28d911204e9022eda172571ca8cc61eaffd942f7/special_tokens_map.json",
14
+ "strip_accents": null,
15
+ "tokenize_chinese_chars": true,
16
+ "tokenizer_class": "BertTokenizer",
17
+ "unk_token": "[UNK]"
18
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.3991290204302646,
4
+ "train_runtime": 1705.6625,
5
+ "train_samples": 5769,
6
+ "train_samples_per_second": 10.147,
7
+ "train_steps_per_second": 0.635
8
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3604536d8dfe8f3cc01f760de64dcbf741c1ddc6fe30bee656a26d7ece4f5c2
3
+ size 3960