feat: upload model
Browse filesupload model, config, tokenizer.json file
upload README.md
- README.md +14 -0
- config.json +29 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# ๐ง๐ปโ๐ป KLUE RoBERTa Large
|
2 |
+
- ์ด ๋ชจ๋ธ์ klue/roberta-large๋ฅผ ํ๊ตญ์ด Machine Reading Comprehension๋ฅผ ์ํด KorQuAD ๋ฐ์ดํฐ 2.1 version 27,423๊ฐ์ ๋ฐ์ดํฐ๋ฅผ ํ์ต์์ผ ๋ง๋ ๋ชจ๋ธ์
๋๋ค.
|
3 |
+
|
4 |
+
# ๐ What Should Know
|
5 |
+
- KorQuAD ์๋ณธ ๋ฐ์ดํฐ๊ฐ ์๋ ํ์ดํผ๋งํฌ, ํ๊ทธ, ์ ๋์ฝ๋ BOM๋ฅผ ์ ๊ฑฐํ์ฌ ํ์ต ํ์๊ณ ,
|
6 |
+
|
7 |
+
# ๐ Getting Started
|
8 |
+
```python
|
9 |
+
from transformers import AutoConfig, AutoModelForQuestionAnswering
|
10 |
+
|
11 |
+
config = AutoConfig.from_pretrained('uomnf97/klue-roberta-finetuned-korquad-v2')
|
12 |
+
tokenizer = AutoTokenizer.from_pretrained('uomnf97/klue-roberta-finetuned-korquad-v2')
|
13 |
+
model = AutoModelForQuestionAnswering.from_pretrained('uomnf97/klue-roberta-finetuned-korquad-v2',config=config)
|
14 |
+
```
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "klue/roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 4096,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 514,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 24,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"tokenizer_class": "BertTokenizer",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.29.2",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32000
|
29 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:139652037217fd89b468e138a39ce1ec8f7dff634ea8b56be7284728d42493e0
|
3 |
+
size 2685100357
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c844a4ff6c4f87e27a8f0606f0420a566c41c1f7cc41d85b797b4fc97e41cf9
|
3 |
+
size 1342574701
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e89d69cb679b8f090f7e6523f5e532965b7f34e7c227eb777923d79340c9377
|
3 |
+
size 14575
|
scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b36a55bcf2baff407691543bae09334561a9cc0288c7d09bc32c0597a006500a
|
3 |
+
size 557
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fcebb672ab2f76eb34287532745ebb230e34a4bcb92fd708a66bc6d6579e589
|
3 |
+
size 627
|
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 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "[CLS]",
|
5 |
+
"do_basic_tokenize": true,
|
6 |
+
"do_lower_case": false,
|
7 |
+
"eos_token": "[SEP]",
|
8 |
+
"mask_token": "[MASK]",
|
9 |
+
"model_max_length": 512,
|
10 |
+
"never_split": null,
|
11 |
+
"pad_token": "[PAD]",
|
12 |
+
"sep_token": "[SEP]",
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "BertTokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3efbc21d48c90b5065460fe64c8f7890a1a4e3d4f7ff964998bd92bd5e84a992
|
3 |
+
size 3963
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|