june42 commited on
Commit
4cf9eb1
โ€ข
1 Parent(s): 5b4ca19

Add v2022 model and ckpt

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. config.json +1 -1
  3. pytorch_model.bin +2 -2
  4. tf_model.h5 +0 -3
  5. vocab.txt +0 -0
README.md CHANGED
@@ -13,7 +13,7 @@ license: "mit"
13
 
14
  ** Updates on 2022.10.08 **
15
 
16
- - KcELECTRA-base-v2022 (๊ตฌ v2022-dev) ๋ชจ๋ธ ์ด๋ฆ„์ด ๋ณ€๊ฒฝ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
17
  - ์œ„ ๋ชจ๋ธ์˜ ์„ธ๋ถ€ ์Šค์ฝ”์–ด๋ฅผ ์ถ”๊ฐ€ํ•˜์˜€์Šต๋‹ˆ๋‹ค.
18
  - ๊ธฐ์กด KcELECTRA-base(v2021) ๋Œ€๋น„ ๋Œ€๋ถ€๋ถ„์˜ downstream task์—์„œ ~1%p ์ˆ˜์ค€์˜ ์„ฑ๋Šฅ ํ–ฅ์ƒ์ด ์žˆ์Šต๋‹ˆ๋‹ค.
19
 
 
13
 
14
  ** Updates on 2022.10.08 **
15
 
16
+ - KcELECTRA-base-v2022 (๊ตฌ v2022-dev) ๋ชจ๋ธ ์ด๋ฆ„์ด ๋ณ€๊ฒฝ๋˜์—ˆ์Šต๋‹ˆ๋‹ค. --> KcELECTRA-base ๋ ˆํฌ์˜ `v2022`๋กœ ํ†ตํ•ฉ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
17
  - ์œ„ ๋ชจ๋ธ์˜ ์„ธ๋ถ€ ์Šค์ฝ”์–ด๋ฅผ ์ถ”๊ฐ€ํ•˜์˜€์Šต๋‹ˆ๋‹ค.
18
  - ๊ธฐ์กด KcELECTRA-base(v2021) ๋Œ€๋น„ ๋Œ€๋ถ€๋ถ„์˜ downstream task์—์„œ ~1%p ์ˆ˜์ค€์˜ ์„ฑ๋Šฅ ํ–ฅ์ƒ์ด ์žˆ์Šต๋‹ˆ๋‹ค.
19
 
config.json CHANGED
@@ -15,7 +15,7 @@
15
  "max_position_embeddings": 512,
16
  "model_type": "electra",
17
  "type_vocab_size": 2,
18
- "vocab_size": 50135,
19
  "pad_token_id": 0,
20
  "tokenizer_class": "BertTokenizer"
21
  }
 
15
  "max_position_embeddings": 512,
16
  "model_type": "electra",
17
  "type_vocab_size": 2,
18
+ "vocab_size": 54343,
19
  "pad_token_id": 0,
20
  "tokenizer_class": "BertTokenizer"
21
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfb914aabf4627728d6494d8acda390a2f26200850a519f4bb55f1297c0ec86a
3
- size 498271049
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3460bb4187cdda4fbc6c8d7dfb97779e43660a86091dc9d1f01810eb5264fe53
3
+ size 511193709
tf_model.h5 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:24b7d452434e965544fc79ab8c56937ef8ea7a153a626381dd09ee8738b4fd42
3
- size 498456784
 
 
 
 
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff