Downloads Β· 30 days
6
4% of all-time downloads
jungmookkim/klue-roberta-base-klue-sts-mrc
klue-roberta-base-klue-sts-mrc is a sentence similarity model from jungmookkim. Use it when you need a score for how close two texts are. It is set up for sentence-transformers.
This is a sentence-transformers model finetuned from shangrilar/klue-roberta-base-klue-sts. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semanβ¦
Downloads Β· 30 days
6
4% of all-time downloads
All-time downloads
164
Public
Parameters
111M
442 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors442 MB Β· 100%
From the Hugging Face model README
This is a sentence-transformers model finetuned from shangrilar/klue-roberta-base-klue-sts. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'RobertaModel'})
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
First install the Sentence Transformers library:
pip install -U sentence-transformers
Then you can load this model and run inference.
from sentence_transformers import SentenceTransformer
# Download from the π€ Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
'μμ΄ν°5μ νλ©΄ ν¬κΈ°λ?',
'2011λ
10μ μ ν μ°½μ
μ μ€ν°λΈ μ‘μ€κ° μΈμμ λ λ¬μ λ βμ‘μ€ νκ΄β μκΈ°κ° λμλ€. νκ³μκ° μνλ λͺ»νλ μ‘μ€ μν₯λ ₯μ΄ μλ 컀μ μ νμ΄ νλ ν΄λ μ κ΅΄λ¬κ° κ²μ΄λ μκΈ°μλ€. μ€μ λ‘ μ νμ μλ
κ°μκΉμ§ 1λ
λμμ μνλ λ―νλ€. μ£Όκ°λ μ²μ λΆμ§λ‘ μΉμμλ€. κ·Έλ¬λ 겨μΈλ‘ μ μ΄λ€λ©΄μ λΆμκΈ°κ° λ¬λΌμ‘λ€. μ‘μ€μ λ§μ μ΄ λλ¬λ€λλ, νμ μ΄ λ©μ·λ€λ μκΈ°κ° λμ€κΈ° μμνλ€.ν μΏ‘μ μ΅κ³ κ²½μμ(CEO)λ‘ μ·¨μν μ΄ν κΉμ§ λλ λ§ν κ²μ 보μ¬μ£Όμ§ λͺ»νλ€. μΏ‘μ 첫 λ²μ§Έ μμ΄ν°μ μλ
κ°μμ λ΄λμ μμ΄ν°5λΌκ³ ν μ μλ€. μ΄ ν°μ 4μΈμΉλ‘ νλ©΄μ΄ μ»€μ‘λλ°λ λ κ°λ²Όμμ§κ³ λ μμμ‘λ€. λμμΈ μΈ‘λ©΄μμλ νμ μ μ΄μλ€. κ·Έλ¬λ λμμΈ λ§κ³ λ κΉμ§ λλ λ§ν κ² μμλ€. νΉν ꡬκΈμ§λλ₯Ό λ체ν μ νμ§λκ° λ¬Έμ κ° λλ€. νκ²μ§κ² νμ¬νλμ§ μν°λ¦¬μλ€. κΈΈμ΄ κ΅¬κ²¨μ§κ³ λ€λ¦¬κ° λκΈ°λ λ± μ ν μ νλ΅μ§ μμλ€.μμ₯μ μ λνλ βμΉ΄ν
κ³ λ¦¬ 리λβλ‘μ μμλ μ½ν΄μ‘λ€. μ νμ μ΄λ μκ°λΆν° μΌμ±μ λ°λΌνκΈ° μμνλ€. μΌμ±μ΄ 4μΈμΉ, 5μΈμΉλμ ν° νλ©΄ κ°€λμν°μΌλ‘ μΈκΈ°λ₯Ό λμ 3.5μΈμΉ μμ΄ν° νλ©΄μ 4μΈμΉλ‘ ν€μ λ€. μμ΄ν¨λλ λ§μ°¬κ°μ§. μ‘μ€λ μμ μ 7μΈμΉλ μΌμ± κ°€λμνμ λν΄ βD.O.A.(λμ€μλ§μ μ¬λ§)βλΌκ³ μ
λ΄μ νμ§λ§ κ·Έκ° μΈμμ λ λ μ§ 1λ
ν μ νμ 7μΈμΉλ μμ΄ν¨λ λ―Έλλ₯Ό λ΄λμλ€.λ°μ§κ³ 보면 βμ νμ νμ βμ βμ‘μ€μ λ§μ βμ΄μλ€. μ‘μ€λ κ°λ ₯ν 카리μ€λ§λ‘ μ‘°μ§μ μ΄λμκ³ μλΉμ μ
μ₯μμ λν
μΌμ κΌΌκΌΌνκ² μ±κ²Όλ€. μμ΄νμΌλ‘ μμ
μμ₯μ νμ ν λ μλ°μ¬μ
μλ€μ μ€λν κ²λ μ‘μ€μκ³ , μμ΄ν°μ λ΄λκΈ° μ μ λ―Έκ΅ μ΄λν΅μ μ¬ AT&Tλ₯Ό μ€λν κ²λ μ‘μ€μλ€. λ°λ©΄ μΏ‘μ μΈκ³ μ΅λ(κ°μ
μ 7μ΅λͺ
) μ΄λν΅μ μ¬μΈ μ°¨μ΄λλͺ¨λ°μΌμ μ€λνμ§ λͺ»ν΄ μ€κ΅ μμ₯μμ κ³ μ νκ³ μλ€.κ²½μμ¬λ€μ΄ μ΄μ ν λ§νΌ νλ€λ μ λ μ ννν
λ μν μμλ€. μ νμ μΌμ±μ΄ νΉνλ₯Ό μΉ¨ν΄νλ€λ©° ν΅μ μκΈ μμ‘μ λ²μμ§λ§ μ€λ¦¬λ μ±κΈ°μ§ λͺ»ν μ± μΌμ± μμλ§ λμ¬μ€¬λ€. μΌμ±μ μ€λ§νΈν° 1μ μ
μ²΄λ‘ μ¬λΌμ°λ€. μλ
4λΆκΈ°μ μ νμ΄ μμ΄ν°μ 4780λ§λ νλ§€ν λ°λ©΄ μΌμ±μ μ€λ§νΈν°μ 6000λ§λ μ΄μ(μΆμ μΉ) νμλ€. νλΈλ¦Ώ μμ₯μμλ μ ν λ
무λκ° νλ€λ¦¬κ³ μλ€. μμ΄ν¨λλ 2010λ
4μ λ°λ§€ ν 2~3λ
λμ μμ₯μ λ
μ νλ€μνΌ νλ€. κ²½μμ¬λ€μ΄ μλ°± μ’
μ νλΈλ¦Ώ μ νμ λ΄λκ³ λ€λ³μ§λ§ λͺ¨λ μ°Έν¨νλ€. κ·Έλ¬λ μλ
νλ°κΈ°λΆν° λ¬λΌμ§κ³ μλ€. λ₯μμ€7, κ°€λμλ
ΈνΈ10.1 λ±μ΄ νΈνμ λ°κ³ μλ€. μ¬ν΄λ μλλ‘μ΄λ μ§μμ 곡μΈκ° λμ± κ±°μΈμ§κ³ μλ μ§μλ κ°μΈν κ²μΌλ‘ μμλλ€.μ νμ΄ μ νTVλ‘ νμ μ μ΄μ΄κ° κ²μ΄λ μκΈ°λ μλ€. μ‘μ€κ° μ νTVμ λν΄ βμ·¨λ―ΈβλΌκ³ λ§νλ©΄μλ λ§λ
μ μ¬νμ κΈ°μΈμκ³ μΏ‘λ βν° κ΄μ¬μ κ°μ§κ³ μλ€βκ³ λ§νμΌλ μ°λ§κ» νμ μ μΈ μ νTVκ° λμ¬ κ°λ₯μ±μ μλ€. κ·Έλ¬λ TV μμ₯μ μΌμ± LG λ±μ΄ μ΄λ―Έ μ₯μ
νκ³ μκ³ κ΅κ°λ§λ€ μΌμ΄λΈ μ¬μ
μ, μ½ν
μΈ μ¬μ
μλ€κ³Ό νμν΄μΌ ν΄ μ€λ§νΈν°κ³Ό λ¬λ¦¬ λ¨μ¨μ μΈκ³ μμ₯μ μ₯μ
νκΈ΄ μ΄λ ΅λ€.',
'μ λλ©μ΄μ
μ λ¬Έ μ±λ μ λμ, μ λλ°μ€(λν: κ³½μλΉ)μ΄ μ€λ ν¬λ¦¬μ€λ§μ€λ₯Ό λ§μ ν¬λ¦¬μ€λ§μ€ μ΄λΈ(λͺ©)μ λΉμΌ(κΈ) μμΌκ° ν¬λ¦¬μ€λ§μ€ νΉμ§ λ°©μ‘μ λ°©μνλ€. λ€κ°μ€λ μ΄λ² ν¬λ¦¬μ€λ§μ€λ μ¬λ λμλ λ¬λ¦¬ μΈμΆμ μμ νλ©΄μ κ°μ‘±λ€κ³Ό μμ νκ² λ³΄λ΄μΌ ν μκΈ°μ΄λ€. μ§μμ λ°λ»ν ν¬λ¦¬μ€λ§μ€ λΆμκΈ°λ₯Ό μ¦κΈΈ μ μλλ‘ μ λλ°μ€, μ λμμμ ν¬λ¦¬μ€λ§μ€νΉμ§ λ°©μ‘μ μ€λΉνλ€. [μ λμ] β· 12μ 24μΌ(λͺ©) β κ·Ήμ₯ν 짱ꡬλ λͺ»λ§λ €, μλ
μλμΌ3 λ± λ°©μ β· 12μ 25μΌ(κΈ) β κ·Ήμ₯ν λλΌμλͺ½, μ λλΌμλͺ½ μ€νμ
2κΈ° λ± λ°©μ [μ λλ°μ€] β· 12μ 24μΌ(λͺ©) β κ·Ήμ₯ν λ½λ‘λ‘, λ°κΌ¬λ°λ νλ μ¦ λ± λ°©μ β· 12μ 25μΌ(κΈ) β λ½λ‘λ‘ λνλλΌ, λΌλ° μΈ λ΄μ, λΌλ° μμΌλλ λ± λ°©μ μ λμ μ±λμμλ βν¬λ¦¬μ€λ§μ€ ννν°β 컨μ
μΌλ‘ 12μ 24μΌ(λͺ©) 11μλΆν° κ·Ήμ₯ν 짱ꡬλ λͺ»λ§λ €μ μλ
μλμΌ3κ° λ°©μλκ³ ν¬λ¦¬μ€λ§μ€ λΉμΌμΈ 12μ 25μΌ(κΈ)μλ μ μμΈ κ·Ήμ₯ν λλΌμλͺ½-μ§κ΅¬μ ꡬλ¦μκ΅κ³Ό μ λλΌμλͺ½ μ리μ¦λ₯Ό μ€μ 8μλΆν° λ§λλ³Ό μ μλ€. ννΈ, μ λλ°μ€ μ±λμμλ βMerry μ λλ°μ€β 컨μ
μΌλ‘ 12μ 24μΌ(λͺ©) μ€μ 8μλΆν° κ·Ήμ₯ν λ½λ‘λ‘μ μ μμΈ λ°κΌ¬λ°λ νλ μ¦κ° λ°©μλκ³ ν¬λ¦¬μ€λ§μ€ λΉμΌ, 12μ 25μΌ(κΈ)μλ μ μμΈ λ½λ‘λ‘ λνλλΌλ₯Ό μ€μ 8μμ 첫 곡κ°ν μμ μ΄λ€. κ·Έ λΏλ§ μλλΌ, λΌλ° μ리μ¦μ κ·Ήμ₯ν 짱ꡬλ λͺ»λ§λ €κΉμ§ μ°μμΌλ‘ λ§λλ³Ό μ μλ€.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.6753, 0.0320],
# [0.6753, 1.0000, 0.0451],
# [0.0320, 0.0451, 1.0000]])
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
| sentence_0 | sentence_1 | |
|---|---|---|
| type | string | string |
| details | <ul><li>min: 8 tokens</li><li>mean: 17.58 tokens</li><li>max: 41 tokens</li></ul> | <ul><li>min: 232 tokens</li><li>mean: 438.28 tokens</li><li>max: 512 tokens</li></ul> |
| sentence_0 | sentence_1 |
|---|---|
| <code>νμ¬μ κ²½κΈ° μν©μ λνλ΄λ μ§νλ μ μμ λΉν΄ λͺ ν¬μΈνΈ μμΉνμλκ°?</code> | <code>μμΆ λΆμ§μ΄ μ΄μ΄μ§λ©΄μ μ°μ μμ°μ΄ 3κ°μ μ°μ κ°μμΈλ₯Ό λνλλ€.30μΌ ν΅κ³μ²μ΄ λ°νν β5μ μ°μ νλλν₯βμ λ°λ₯΄λ©΄ μ 체 μ°μ μμ°μ μ λ¬μ λΉν΄ 0.6% μ€μλ€. μ§λ 3μ μ΄ν μ λ¬ μ°μ κ°μμΈλ€.λΆλ¬Έλ³λ‘λ μ μ‘°μ λ±μ΄ ν¬ν¨λ κ΄κ³΅μ μμ°μ΄ μ λ¬λ³΄λ€ 1.3% κ°μνλ€. ν΅μ Β·λ°©μ‘μ₯λΉ(22.1%)μ μμ μ μ (3.0%)λ λμμ§λ§ μλμ°¨(-3.7%)μ λ°λ체(-4.8%) λ±μ λΆμ§νλ€. μμΆ κ°μ μν₯μ΄ μ»Έλ€. λ°λ체(-7.9%)μ μλμ°¨(-3.5%), ννμ ν(-4.3%) λ± μ£Όλ ₯ νλͺ©μ μμΆμ΄ λͺ¨λ λ·κ±Έμμ§ μ³€λ€. μ¬κ³ μ¨(μΆνλ λλΉ μ¬κ³ λΉμ¨)μ 127.3%λ‘ μ μλ³΄λ€ 0.1%ν¬μΈνΈ λμ΄λ¬λ€. 2008λ 12μ(129.9%) μ΄ν 77κ°μ λ§μ κ°μ₯ λμ μμΉλ€. μ μ‘°μ νκ· κ°λλ₯ μ 0.7%ν¬μΈνΈ λ¨μ΄μ§ 73.4%μλ€.νμ¬μ κ²½κΈ° μν©μ 보μ¬μ£Όλ κ²½κΈ°λνμ§μ μνλ³λμΉλ 0.5ν¬μΈνΈ νλ½νλ€. λ°λ©΄ ν₯ν κ²½κΈ°λ₯Ό μ¬λ μ£λμΈ μ νμ§μ μνλ³λμΉλ 0.3ν¬μΈνΈ μμΉνλ€. κΉλ³ν κΈ°νμ¬μ λΆ κ²½μ λΆμκ³Όμ₯μ βμ€λνΈν‘κΈ°μ¦νκ΅°(MERSΒ·λ©λ₯΄μ€)κ³Ό κ·Έλ¦¬μ€ μ±λ¬΄νμ λ± λλ΄μΈ μνμμΈμ΄ νλλΌ λΆμ§μ΄ μ§μλ μ μλ€βλ©° βκ²½μ κ° μ μμ ν볡 κΆ€λλ‘ λ³΅κ·ν μ μλλ‘ μΆκ°κ²½μ μμ° λ± 15μ‘°μ μ΄μ μ¬μ 보κ°μ μ μνκ² μΆμ§νκ³ λΆμΌλ³ κ²½μ νλ ₯ μ κ³ λμ± μ μ°¨μ§μμ΄ μΆμ§νκ² λ€βκ³ λ§νλ€.</code> |
| <code>μ¬λ² μ΄νμ μ‘°κ΅μ 2012λ κ²½λ§€μμ₯ κ±°λμ‘μ?</code> | <code>μ λ½ κ²½μ μκΈ°μλ λΆκ΅¬νκ³ μΈκ³ λ―Έμ μμ₯μ μ±μ₯μΈλ₯Ό μ΄μ΄κ°κ³ μλ€.νλμ€ λ―Έμ μ 보μ 체 μνΈνλΌμ΄μ€λ·μ»΄μ΄ μ΅κ·Ό λ°νν β2012λ μΈκ³ λ―Έμ μμ₯ λΆμβμ λ°λ₯΄λ©΄ μλ μΈκ³ λ―Έμ ν κ²½λ§€μμ₯μλ 122μ΅λ¬λ¬(μ½ 13μ‘°μ)μ βλμΉ«λβμ΄ λͺ°λ Έλ€. 2011λ μ 115μ΅λ¬λ¬λ³΄λ€ 6% μ λ λμ΄λ κ·λͺ¨λ€.μ§λν΄ κ²½λ§€μμ₯μμ μν κ±°λμ‘μ΄ κ°μ₯ μ»Έλ μκ°λ μ€λ μνλ‘, 3μ΅2900λ§λ¬λ¬μ΄μΉκ° κ±°λλλ€. μ€λμνμ¬λ¨μ΄ μλ 11μλΆν° κ²½λ§€λ₯Ό ν΅ν΄ 2λ§μ¬μ μ μ€ν¬μ€ν¬λ¦° μΈμν, νν, μ½λΌμ£Ό, νν, μ¬μ§ λ±μ νμκΈ° λλ¬ΈμΌλ‘ νμ΄λλ€.μ₯λ€μ²Έ(2μ΅8722λ§λ¬λ¬), νλΈλ‘ νΌμΉ΄μ(2μ΅8614λ§λ¬λ¬), μΉλ°μ΄μ€(2μ΅7019λ§λ¬λ¬), κ²λ₯΄νλ₯΄νΈ 리νν°(2μ΅6280λ§λ¬λ¬), μ¬λ² μ΄ν(1μ΅7578λ§λ¬λ¬), 리컀λ(1μ΅6679λ§λ¬λ¬), λ§ν¬ λ‘μ€μ½(1μ΅6678λ§λ¬λ¬), νλμμ€ λ² μ΄μ»¨(1μ΅5308λ§λ¬λ¬) , νΈλ°μ€μ€(1μ΅5207λ§λ¬λ¬)λ λμ°°μ΄μ‘ βν±10βμ λ€μλ€. κ΅λ΄ μκ°λ‘λ μ΄μ°ν(188μ, 1000λ§λ¬λ¬) κΉνκΈ°(257μ, 689λ§λ¬λ¬) λ°μκ·Ό(292μ, 597λ§λ¬λ¬) λ±μ μν κ±°λμ‘μ΄ ν° κ²μΌλ‘ μ‘°μ¬λλ€.κ΅μ λ―Έμ μμ₯μμ μ€κ΅ μκ°λ€μ μ½μ§λ μ΄μ΄μ‘λ€. μν κ±°λμ‘ μμ 10μκΆμ μ€κ΅ μκ³ μκ° μ₯λ€μ²Έ(2μ), μΉλ°μ΄μ€(4μ), μ¬λ² μ΄ν(6μ), 리컀λ(7μ), νΈλ°μ€μ€(10μ) λ± 5λͺ μ΄ μ΄λ¦μ μ¬λ Έλ€.μ€κ΅ κ²½λ§€μμ₯λ 50μ΅λ¬λ¬λ‘ κ΅μ μμ₯μ 41%λ₯Ό μ°¨μ§νλ©° 2λ μ§Έ 1μλ₯Ό κΈ°λ‘νλ€. μ€κ΅κ³Ό νκ΅κΆ λΆμ μΈ΅ 컬λ ν°λ€μ΄ μκ΅μ κ·Έλ¦Όμ μ¬λ€μ΄λ©΄μ κ΅μ λ―Έμ κ³μ βμ°¨μ΄λ νμβκ° νμ±λκ³ μλ€κ³ μ λ¬Έκ°λ€μ λΆμνκ³ μλ€. μ€κ΅ λ€μμΌλ‘ λ―Έκ΅(27%) μκ΅(18%) νλμ€(4%)κ° λ€λ₯Ό μ΄μλ€.</code> |
| <code>μΌμ½ μ€νμ΄μ μ ν μ§μμλ€μ΄ λͺ¨λ κ³Όμ μ λν΄ μκ² λλ λ μ μΈμ μΈκ°?</code> | <code>βμΊ μ½λ μ μ¬μλμ μ§λ μΈμ¬λ₯Ό λ½κΈ° μν΄ μ€νμ΄μ μ νμ λμ νκ² λμ΅λλ€.βμ΅μ©μ± μΊ μ½ μΈμ¬νμ₯(μ¬μ§)μ μ€νμ΄μ μ ν λμ λ°°κ²½μ λν΄ μ΄λ κ² λ§νλ€. μ΅ νμ₯μ βνλ ₯λ³΄λ€ λ₯λ ₯μ μ€μνλ βμ΄λ¦° μ±μ©βμ μν΄ μ±μ© κ΄νμ μ λ©΄ κ°νΈνλ€βκ³ μ€λͺ νλ€.μ€νμ΄μ μ ν κ³Όμ λ 4κ°λ‘ μ€μ¬ μ§μμλ€μ λΆλ΄μ μ΅μννκΈ°λ‘ νλ€. λ€λ§ μ΄λ¦, μ΄λ©μΌ, μλ μμΌλ§ κΈ°μ νλ μ μ¬μ§μκ³Ό λμμ κ³Όμ 2κ°κ° μ£Όμ΄μ§λ€. μ΄ κ³Όμ λ 6μ2μΌ μ€ν 6μκΉμ§ μ μΆν΄μΌ νλ€. λλ¨Έμ§ κ³Όμ 2κ°λ 6μ3μΌ μ€μ 곡μ§νλ©°, κ·Έλ λͺ¨λ μ μΆν΄μΌ νλ€.λ€ κ°μ§ κ³Όμ λ₯Ό μ μΆνκ³ μνΈνκ°κΉμ§ μνν΄μΌ μ ν¨ν μ μ¬μ§μμ΄ λλ€. μ΅ νμ₯μ βκ³Όμ λ μ΄λ€ μΌμ΄ μμ΄λ μ μλ μκ°μ μμν΄μΌ νλ€βλ©° βννμ±μ μν΄ λ―Έμ μΆ λ λͺ¨λ νλ½νκ² λλ€βκ³ λ§νλ€. μΊ μ½λ λ€λ₯Έ 곡기μ μ€νμ΄μ μ νμμ λμ ν λμμ μ μμ νμ§ μκΈ°λ‘ νλ€. μ§μμμ λΆλ΄μ μ€μ΄κΈ° μν΄μλ€. νΉν μΊ μ½λ κ³Όμ μμμ λͺ¨λμκ² 5λ μ°¨ λ―Έλ§μ μ λ°° νκ°λ₯Ό λ°λλ‘ ν λ°©μΉ¨μ΄λ€.μΊ μ½λ μ΄λ² μ±μ©μ ν΅ν΄ νΉλ³ν 결격μ¬μ κ° μλ ν μΈν΄μλ£μ λλΆλΆμ μ κ·μ§μΌλ‘ μ νν μμ μ΄λ€. μ§λν΄μλ 60%μλ μ κ·μ§ μ νμ¨μ μ¬ν΄λ 90% μ΄μμΌλ‘ λμΈλ€λ λ°©μΉ¨μ΄λ€. μ§λν΄ μ μ¬ν μΊ μ½ μ μ μ¬μ 60λͺ κ°μ΄λ° μ‘°κΈ°ν΄μ¬μλ 2λͺ μ λΆκ³Όνλ€.</code> |
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"gather_across_devices": false
}
per_device_train_batch_size: 16per_device_eval_batch_size: 16num_train_epochs: 1batch_sampler: no_duplicatesmulti_dataset_batch_sampler: round_robinoverwrite_output_dir: Falsedo_predict: Falseeval_strategy: noprediction_loss_only: Trueper_device_train_batch_size: 16per_device_eval_batch_size: 16per_gpu_train_batch_size: Noneper_gpu_eval_batch_size: Nonegradient_accumulation_steps: 1eval_accumulation_steps: Nonetorch_empty_cache_steps: Nonelearning_rate: 5e-05weight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08max_grad_norm: 1num_train_epochs: 1max_steps: -1lr_scheduler_type: linearlr_scheduler_kwargs: {}warmup_ratio: 0.0warmup_steps: 0log_level: passivelog_level_replica: warninglog_on_each_node: Truelogging_nan_inf_filter: Truesave_safetensors: Truesave_on_each_node: Falsesave_only_model: Falserestore_callback_states_from_checkpoint: Falseno_cuda: Falseuse_cpu: Falseuse_mps_device: Falseseed: 42data_seed: Nonejit_mode_eval: Falsebf16: Falsefp16: Falsefp16_opt_level: O1half_precision_backend: autobf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonelocal_rank: 0ddp_backend: Nonetpu_num_cores: Nonetpu_metrics_debug: Falsedebug: []dataloader_drop_last: Falsedataloader_num_workers: 0dataloader_prefetch_factor: Nonepast_index: -1disable_tqdm: Falseremove_unused_columns: Truelabel_names: Noneload_best_model_at_end: Falseignore_data_skip: Falsefsdp: []fsdp_min_num_params: 0fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap: Noneaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}parallelism_config: Nonedeepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torch_fusedoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthproject: huggingfacetrackio_space_id: trackioddp_find_unused_parameters: Noneddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falsedataloader_pin_memory: Truedataloader_persistent_workers: Falseskip_memory_metrics: Trueuse_legacy_prediction_loop: Falsepush_to_hub: Falseresume_from_checkpoint: Nonehub_model_id: Nonehub_strategy: every_savehub_private_repo: Nonehub_always_push: Falsehub_revision: Nonegradient_checkpointing: Falsegradient_checkpointing_kwargs: Noneinclude_inputs_for_metrics: Falseinclude_for_metrics: []eval_do_concat_batches: Truefp16_backend: autopush_to_hub_model_id: Nonepush_to_hub_organization: Nonemp_parameters:auto_find_batch_size: Falsefull_determinism: Falsetorchdynamo: Noneray_scope: lastddp_timeout: 1800torch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneinclude_tokens_per_second: Falseinclude_num_input_tokens_seen: noneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falseeval_on_start: Falseuse_liger_kernel: Falseliger_kernel_config: Noneeval_use_gather_object: Falseaverage_tokens_across_devices: Trueprompts: Nonebatch_sampler: no_duplicatesmulti_dataset_batch_sampler: round_robinrouter_mapping: {}learning_rate_mapping: {}| Epoch | Step | Training Loss |
|---|---|---|
| 0.4558 | 500 | 0.1572 |
| 0.9116 | 1000 | 0.1101 |
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->