KuKu
dragonkue
AI & ML interests
anything.
Recent Activity
liked a dataset about 19 hours ago
lightonai/embeddings-fine-tuning-filtered-en upvoted an article about 21 hours ago
GLInt: Geometry-Matched Hard Negatives for Late-Interaction Retrieval upvoted a paper about 22 hours ago
Compact Language Models via Pruning and Knowledge DistillationOrganizations
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 • 79.7k • 24 -
BAAI/bge-reranker-v2-m3
Text Classification • 0.6B • Updated • 17.6M • • 1.13k -
telepix/PIXIE-Spell-Reranker-Preview-0.6B
Text Ranking • 0.6B • Updated • 71 • 5 -
Qwen/Qwen3-Reranker-0.6B
Text Ranking • 0.6B • Updated • 2.66M • 387
A collection of high-performance Korean embedding models, including both models I trained myself and other publicly available strong baselines.
-
sionic-ai/comsat-embed-ko-8b-preview
Sentence Similarity • 8B • Updated • 431 • 16 -
dragonkue/snowflake-arctic-embed-l-v2.0-ko
Sentence Similarity • 0.6B • Updated • 74.8k • • 50 -
dragonkue/BGE-m3-ko
Sentence Similarity • 0.6B • Updated • 260k • • 78 -
dragonkue/multilingual-e5-small-ko
Sentence Similarity • 0.1B • Updated • 2.51k • • 11
A collection of multilingual embedding models suitable for use as training backbones
-
BAAI/bge-m3
Sentence Similarity • Updated • 32.4M • • 3.38k -
Snowflake/snowflake-arctic-embed-l-v2.0
Sentence Similarity • 0.6B • Updated • 740k • • 250 -
google/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 2.11M • • 1.83k -
lightonai/mDenseOn
Sentence Similarity • 0.3B • Updated • 1.5k • • 13
A collection of backbone models suitable for building Korean embedding or reranker models.
A collection of high-performance Korean embedding models, including both models I trained myself and other publicly available strong baselines.
-
sionic-ai/comsat-embed-ko-8b-preview
Sentence Similarity • 8B • Updated • 431 • 16 -
dragonkue/snowflake-arctic-embed-l-v2.0-ko
Sentence Similarity • 0.6B • Updated • 74.8k • • 50 -
dragonkue/BGE-m3-ko
Sentence Similarity • 0.6B • Updated • 260k • • 78 -
dragonkue/multilingual-e5-small-ko
Sentence Similarity • 0.1B • Updated • 2.51k • • 11
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 • 79.7k • 24 -
BAAI/bge-reranker-v2-m3
Text Classification • 0.6B • Updated • 17.6M • • 1.13k -
telepix/PIXIE-Spell-Reranker-Preview-0.6B
Text Ranking • 0.6B • Updated • 71 • 5 -
Qwen/Qwen3-Reranker-0.6B
Text Ranking • 0.6B • Updated • 2.66M • 387
A collection of multilingual embedding models suitable for use as training backbones
-
BAAI/bge-m3
Sentence Similarity • Updated • 32.4M • • 3.38k -
Snowflake/snowflake-arctic-embed-l-v2.0
Sentence Similarity • 0.6B • Updated • 740k • • 250 -
google/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 2.11M • • 1.83k -
lightonai/mDenseOn
Sentence Similarity • 0.3B • Updated • 1.5k • • 13
A collection of backbone models suitable for building Korean embedding or reranker models.