jiakai's picture

234 835

jiakai

real-jiakai

·

https://blog.gujiakai.top

AI & ML interests

LLM && Smart QA

Recent Activity

liked a model about 2 hours ago

Qwen/QwQ-32B

liked a model about 5 hours ago

tngtech/DeepSeek-R1T-Chimera

liked a Space about 24 hours ago

mozilla-ai/document-to-markdown

View all activity

Organizations

real-jiakai's activity

upvoted 2 articles about 24 hours ago

Article

Cohere on Hugging Face Inference Providers 🔥

12 days ago

• 124

Article

17 Reasons Why Gradio Isn't Just Another UI Library

12 days ago

• 25

upvoted a collection about 24 hours ago

ReSearch

Trained models as described in the paper "ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning" • 5 items • Updated Mar 27 • 5

upvoted an article 2 days ago

Article

Tiny Agents: a MCP-powered agent in 50 lines of code

3 days ago

• 148

upvoted a collection 2 days ago

DistilBERT release

Original DistilBERT model, checkpoints obtained from using teacher-student learning from the original BERT checkpoints. • 6 items • Updated Apr 17, 2024 • 21

upvoted 2 papers 4 days ago

The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks

Paper • 2504.15521 • Published 6 days ago • 60

Kuwain 1.5B: An Arabic SLM via Language Injection

Paper • 2504.15120 • Published 7 days ago • 112

upvoted 4 papers 5 days ago

Learning to Reason under Off-Policy Guidance

Paper • 2504.14945 • Published 7 days ago • 76

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models

Paper • 2504.13367 • Published 10 days ago • 24

FlowReasoner: Reinforcing Query-Level Meta-Agents

Paper • 2504.15257 • Published 7 days ago • 45

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

Paper • 2504.15271 • Published 7 days ago • 63

upvoted 2 papers 6 days ago

Could Thinking Multilingually Empower LLM Reasoning?

Paper • 2504.11833 • Published 12 days ago • 26

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Paper • 2504.13837 • Published 10 days ago • 111

upvoted an article 7 days ago

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Sep 18, 2024

• 238

upvoted a paper 7 days ago

LettuceDetect: A Hallucination Detection Framework for RAG Applications

Paper • 2502.17125 • Published Feb 24 • 11

upvoted a collection 7 days ago

Hallucination detection

Trained ModernBERT (base and large) for detection hallucinations in LLM responses. The models are trained as token classifications. • 4 items • Updated Mar 5 • 16

upvoted a collection 10 days ago

MAI-DS-R1

MAI-DS-R1 is a DeepSeek-R1 reasoning model that has been post-trained by the Microsoft AI team. • 2 items • Updated 11 days ago • 9

upvoted an article 10 days ago

Article

Introducing HELMET

12 days ago

• 22