KuKu

dragonkue's activity

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

upvoted a paper 3 days ago

ReasonIR: Training Retrievers for Reasoning Tasks

Paper • 2504.20595 • Published 10 days ago • 50

liked a model 3 days ago

infly/inf-retriever-v1-1.5b

Sentence Similarity • Updated Mar 28 • 23.1k • 29

liked a model 8 days ago

microsoft/Phi-4-reasoning

Text Generation • Updated about 7 hours ago • 5.62k • 156

liked a model 14 days ago

Skywork/Skywork-R1V2-38B

Image-Text-to-Text • Updated 12 days ago • 12.1k • 116

liked a model 17 days ago

microsoft/bitnet-b1.58-2B-4T

Text Generation • Updated 8 days ago • 84.8k • 948

updated 2 collections 17 days ago

Korean Reranker Models

Collection

Korean reranker models that improve retrieval accuracy by re-ranking candidates based on query relevance. • 1 item • Updated 17 days ago

Korean Embedding Models

Collection

A collection of embedding models that are optimized for understanding and representing Korean text. • 2 items • Updated 17 days ago

liked a model 19 days ago

mixedbread-ai/mxbai-rerank-xsmall-v1

Text Ranking • Updated Apr 2 • 145k • 41

upvoted an article about 1 month ago

view article

Article

Preference Tuning LLMs with Direct Preference Optimization Methods

Jan 18, 2024

• 57

upvoted a paper about 1 month ago

Understanding R1-Zero-Like Training: A Critical Perspective

Paper • 2503.20783 • Published Mar 26 • 48

New activity in dragonkue/bge-reranker-v2-m3-ko about 1 month ago

Update model metadata to set pipeline tag to the new `text-ranking`

1

#3 opened about 1 month ago by

tomaarsen

upvoted an article about 1 month ago

view article

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

Mar 26

• 125

upvoted an article about 2 months ago

view article

Article

What Makes a Dialog Agent Useful?

Jan 24, 2023

• 2

updated a model about 2 months ago

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

Sentence Similarity • Updated Mar 19 • 5.67k • 26

upvoted a collection about 2 months ago

EXAONE-Deep

Collection

EXAONE reasoning model series of 2.4B, 7.8B, and 32B, optimized for reasoning tasks including math and coding • 9 items • Updated Mar 18 • 86

liked 2 models about 2 months ago

mistralai/Mistral-Small-3.1-24B-Instruct-2503

Image-Text-to-Text • Updated about 1 month ago • 105k • • 1.2k

Tower-Babel/Babel-9B-Chat

Updated Mar 19 • 1.87k • 50

upvoted a paper about 2 months ago

Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers

Paper • 2503.00865 • Published Mar 2 • 65