KuKu

dragonkue

junhyuk's profile picture

dongbin777's profile picture

exoplanet's profile picture

AI & ML interests

anything.

Recent Activity

upvoted a paper 7 days ago

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

upvoted a collection 9 days ago

Qwen3.5-text-only

upvoted a paper 16 days ago

zELO: ELO-inspired Training Method for Rerankers and Embedding Models

View all activity

Organizations

dragonkue 's collections 7

Korean Embedding Models

A collection of high-performance Korean embedding models, including both models I trained myself and other publicly available strong baselines.

dragonkue/snowflake-arctic-embed-l-v2.0-ko

Sentence Similarity • 0.6B • Updated Oct 16, 2025 • 6.44k • • 45
dragonkue/BGE-m3-ko

Sentence Similarity • 0.6B • Updated Oct 16, 2025 • 141k • • 72
dragonkue/multilingual-e5-small-ko

Sentence Similarity • 0.1B • Updated Oct 16, 2025 • 5.59k • • 10
dragonkue/multilingual-e5-small-ko-v2

Sentence Similarity • 0.1B • Updated Oct 16, 2025 • 4.17k • • 2

Multilingual Embedding Models

A collection of multilingual embedding models suitable for use as training backbones

google/embeddinggemma-300m

Sentence Similarity • 0.3B • Updated Sep 25, 2025 • 1.8M • • 1.54k
BAAI/bge-m3

Sentence Similarity • Updated Jul 3, 2024 • 16.6M • • 2.84k
Snowflake/snowflake-arctic-embed-l-v2.0

Sentence Similarity • 0.6B • Updated Jul 28, 2025 • 716k • • 236
intfloat/multilingual-e5-large-instruct

Feature Extraction • 0.6B • Updated Jul 10, 2025 • 1.13M • • 608

Colbert (multi-vec)

dragonkue/colbert-ko-0.1b

Sentence Similarity • 0.1B • Updated Jan 25 • 460 • 4
LiquidAI/LFM2-ColBERT-350M

Sentence Similarity • 0.4B • Updated Dec 5, 2025 • 2.23k • 125
yjoonjang/colbert-ko-v1

Sentence Similarity • 0.1B • Updated Nov 28, 2025 • 15 • 14
mixedbread-ai/mxbai-edge-colbert-v0-32m

Sentence Similarity • 31.9M • Updated Feb 14 • 54k • • 39

Korean BERT

A collection of backbone models suitable for building Korean embedding or reranker models.

skt/A.X-Encoder-base

Text Classification • 0.1B • Updated Jan 20 • 1.16k • 27

Reranker Models

A collection of high-performance Korean reranker models, including those I have trained myself as well as other strong baselines

dragonkue/bge-reranker-v2-m3-ko

Text Ranking • 0.6B • Updated Apr 3, 2025 • 49.3k • 20
telepix/PIXIE-Spell-Reranker-Preview-0.6B

Text Ranking • 0.6B • Updated Sep 19, 2025 • 52 • 5
BAAI/bge-reranker-v2-m3

Text Classification • 0.6B • Updated Jun 24, 2024 • 5.03M • • 927
Qwen/Qwen3-Reranker-0.6B

Text Ranking • 0.6B • Updated Jun 9, 2025 • 642k • 323

Multi-modal Retrieval Models

Qwen/Qwen3-VL-Embedding-8B

Feature Extraction • Updated Jan 19 • 565k • 366
Qwen/Qwen3-VL-Embedding-2B

Feature Extraction • 2B • Updated Jan 19 • 1.19M • • 350
Qwen/Qwen3-VL-Reranker-8B

Text Ranking • 9B • Updated Jan 19 • 184k • 133
Qwen/Qwen3-VL-Reranker-2B

Text Ranking • Updated Jan 19 • 208k • 180

Korean Sparse Retriever

telepix/PIXIE-Splade-Preview

Feature Extraction • 0.1B • Updated Sep 19, 2025 • 99 • 13
yjoonjang/splade-ko-v1

Feature Extraction • 0.1B • Updated Jan 17 • 2.31k • • 14

Korean Embedding Models

A collection of high-performance Korean embedding models, including both models I trained myself and other publicly available strong baselines.

dragonkue/snowflake-arctic-embed-l-v2.0-ko

Sentence Similarity • 0.6B • Updated Oct 16, 2025 • 6.44k • • 45
dragonkue/BGE-m3-ko

Sentence Similarity • 0.6B • Updated Oct 16, 2025 • 141k • • 72
dragonkue/multilingual-e5-small-ko

Sentence Similarity • 0.1B • Updated Oct 16, 2025 • 5.59k • • 10
dragonkue/multilingual-e5-small-ko-v2

Sentence Similarity • 0.1B • Updated Oct 16, 2025 • 4.17k • • 2

Reranker Models

A collection of high-performance Korean reranker models, including those I have trained myself as well as other strong baselines

dragonkue/bge-reranker-v2-m3-ko

Text Ranking • 0.6B • Updated Apr 3, 2025 • 49.3k • 20
telepix/PIXIE-Spell-Reranker-Preview-0.6B

Text Ranking • 0.6B • Updated Sep 19, 2025 • 52 • 5
BAAI/bge-reranker-v2-m3

Text Classification • 0.6B • Updated Jun 24, 2024 • 5.03M • • 927
Qwen/Qwen3-Reranker-0.6B

Text Ranking • 0.6B • Updated Jun 9, 2025 • 642k • 323

Multilingual Embedding Models

A collection of multilingual embedding models suitable for use as training backbones

google/embeddinggemma-300m

Sentence Similarity • 0.3B • Updated Sep 25, 2025 • 1.8M • • 1.54k
BAAI/bge-m3

Sentence Similarity • Updated Jul 3, 2024 • 16.6M • • 2.84k
Snowflake/snowflake-arctic-embed-l-v2.0

Sentence Similarity • 0.6B • Updated Jul 28, 2025 • 716k • • 236
intfloat/multilingual-e5-large-instruct

Feature Extraction • 0.6B • Updated Jul 10, 2025 • 1.13M • • 608

Multi-modal Retrieval Models

Qwen/Qwen3-VL-Embedding-8B

Feature Extraction • Updated Jan 19 • 565k • 366
Qwen/Qwen3-VL-Embedding-2B

Feature Extraction • 2B • Updated Jan 19 • 1.19M • • 350
Qwen/Qwen3-VL-Reranker-8B

Text Ranking • 9B • Updated Jan 19 • 184k • 133
Qwen/Qwen3-VL-Reranker-2B

Text Ranking • Updated Jan 19 • 208k • 180

Colbert (multi-vec)

dragonkue/colbert-ko-0.1b

Sentence Similarity • 0.1B • Updated Jan 25 • 460 • 4
LiquidAI/LFM2-ColBERT-350M

Sentence Similarity • 0.4B • Updated Dec 5, 2025 • 2.23k • 125
yjoonjang/colbert-ko-v1

Sentence Similarity • 0.1B • Updated Nov 28, 2025 • 15 • 14
mixedbread-ai/mxbai-edge-colbert-v0-32m

Sentence Similarity • 31.9M • Updated Feb 14 • 54k • • 39

Korean Sparse Retriever

telepix/PIXIE-Splade-Preview

Feature Extraction • 0.1B • Updated Sep 19, 2025 • 99 • 13
yjoonjang/splade-ko-v1

Feature Extraction • 0.1B • Updated Jan 17 • 2.31k • • 14

Korean BERT

A collection of backbone models suitable for building Korean embedding or reranker models.

skt/A.X-Encoder-base

Text Classification • 0.1B • Updated Jan 20 • 1.16k • 27