KuKu
dragonkue
AI & ML interests
anything.
Recent Activity
upvoted an article about 14 hours ago
Tokenmaxxing BERT: 50x faster tokenization liked a model about 23 hours ago
KaLM-Embedding/KaLM-Reranker-V1-Large-R2 liked a dataset about 24 hours ago
Shitao/bge-m3-dataOrganizations
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 • 237k • 25 -
BAAI/bge-reranker-v2-m3
Text Classification • 0.6B • Updated • 15.9M • • 1.26k -
telepix/PIXIE-Spell-Reranker-Preview-0.6B
Text Ranking • 0.6B • Updated • 117 • 6 -
Qwen/Qwen3-Reranker-0.6B
Text Ranking • 0.6B • Updated • 1.61M • • 416
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 • 148 • 19 -
dragonkue/snowflake-arctic-embed-l-v2.0-ko
Sentence Similarity • 0.6B • Updated • 131k • 50 -
dragonkue/BGE-m3-ko
Sentence Similarity • 0.6B • Updated • 55.2k • • 77 -
dragonkue/multilingual-e5-small-ko
Sentence Similarity • 0.1B • Updated • 4.59k • • 11
A collection of multilingual embedding models suitable for use as training backbones
-
BAAI/bge-m3
Sentence Similarity • Updated • 32.3M • • 3.9k -
Snowflake/snowflake-arctic-embed-l-v2.0
Sentence Similarity • 0.6B • Updated • 1.08M • • 262 -
google/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 3.21M • • 2.03k -
lightonai/mDenseOn
Sentence Similarity • 0.3B • Updated • 5.23k • • 15
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 • 148 • 19 -
dragonkue/snowflake-arctic-embed-l-v2.0-ko
Sentence Similarity • 0.6B • Updated • 131k • 50 -
dragonkue/BGE-m3-ko
Sentence Similarity • 0.6B • Updated • 55.2k • • 77 -
dragonkue/multilingual-e5-small-ko
Sentence Similarity • 0.1B • Updated • 4.59k • • 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 • 237k • 25 -
BAAI/bge-reranker-v2-m3
Text Classification • 0.6B • Updated • 15.9M • • 1.26k -
telepix/PIXIE-Spell-Reranker-Preview-0.6B
Text Ranking • 0.6B • Updated • 117 • 6 -
Qwen/Qwen3-Reranker-0.6B
Text Ranking • 0.6B • Updated • 1.61M • • 416
A collection of multilingual embedding models suitable for use as training backbones
-
BAAI/bge-m3
Sentence Similarity • Updated • 32.3M • • 3.9k -
Snowflake/snowflake-arctic-embed-l-v2.0
Sentence Similarity • 0.6B • Updated • 1.08M • • 262 -
google/embeddinggemma-300m
Sentence Similarity • 0.3B • Updated • 3.21M • • 2.03k -
lightonai/mDenseOn
Sentence Similarity • 0.3B • Updated • 5.23k • • 15
A collection of backbone models suitable for building Korean embedding or reranker models.