KuKu

dragonkue's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 4 days ago

SauerkrautLM-MoEdernColBERT

Collection

Multilingual ColBERT retrievers on the MoEdernBERT architecture (1.5M, 27M, 115M) with GGUF and CoreML builds • 9 items • Updated 7 days ago • 13

liked a dataset 8 days ago

CohereLabsCommunity/CulturalRiddles

Viewer • Updated 3 days ago • 251k • 520 • 41

upvoted an article 9 days ago

view article

Article

NVIDIA Nemotron 3.5 Embed, Rerank, and Parse: Advancing Agents with World-Class Retrieval Models

• 

nvidia

•

9 days ago

• 63

liked a model 9 days ago

nlpai-lab/KURE-v3

Sentence Similarity • 1B • Updated 9 days ago • 834 • 24

upvoted a collection 9 days ago

KURE

Collection

KURE: Korea University REtrieval models • 9 items • Updated 11 days ago • 10

upvoted an article 10 days ago

view article

Article

SlideOn & mSlideOn: Sparsified Late-Interaction and Dense Retrievers

• 

lightonai

•

11 days ago

• 28

liked a Space 10 days ago

Running

26

HAKARI-Bench Leaderboard

⚖

26

Lightweight multilingual IR benchmark & leaderboard

upvoted an article 10 days ago

view article

Article

mLateOn: A New SoTA for Multilingual ColBERT-Style Retrieval, Evaluated on HAKARI-Bench

• 

hotchpotch

•

Aug 13

• 12

upvoted an article 15 days ago

view article

Article

Tokenmaxxing BERT: 50x faster tokenization

• 

huggingface

•

15 days ago

• 53

liked a model 16 days ago

KaLM-Embedding/KaLM-Reranker-V1-Large-R2

Text Ranking • 8B • Updated Sep 23 • 148 • 4

liked 3 datasets 16 days ago

Shitao/bge-m3-data

Viewer • Updated Apr 26, 2024 • 172k • 646 • 55

KaLM-Embedding/KaLM-embedding-finetuning-data

Viewer • Updated Nov 27, 2025 • 6.34M • 623 • 33

KaLM-Embedding/KaLM-reranker-training-data

Viewer • Updated Sep 4 • 3.89M • 2.09k • 4

upvoted a collection 16 days ago

UltraBERT

Collection

UltraBERT: Beyond the Limit of BERT Pre-Training. Pre-trained 150M/380M encoders and a text embedding model, English, 32K context. • 4 items • Updated 17 days ago • 30

upvoted an article 16 days ago

view article

Article

UltraBERT: One Encoder for Classification and Retrieval

• 

dmis-lab

•

17 days ago

• 66

upvoted a paper 18 days ago

Continually Post-training Small Models via Synthetic Self-distillation

Paper • 2610.13113 • Published 22 days ago • 42

liked 4 models 25 days ago

sionic-ai/comsat-embed-ja-0.3b-preview

Sentence Similarity • 0.3B • Updated Jul 5 • 146 • 1

sionic-ai/comsat-embed-ja-8b-preview

Sentence Similarity • 8B • Updated Jul 5 • 139 • 2

sionic-ai/comsat-embed-ko-8b-preview

Sentence Similarity • 8B • Updated Jul 5 • 145 • 19

sionic-ai/PepperOCR-VL

Image-Text-to-Text • 5B • Updated 26 days ago • 253 • 9