ruins

ruinnight

AI & ML interests

None yet

Recent Activity

upvoted an article 18 days ago

Why We Built VIBE Bench: Rethinking Evaluation for Real Workloads

upvoted an article 18 days ago

M2.1: Multilingual and Multi-Task Coding with Strong Generalization

upvoted an article 3 months ago

History of State Space Models (SSM) in 2022

View all activity

Organizations

None yet

liked 3 Spaces 3 months ago

Unlocking On-Policy Distillation for Any Model Family

📝

Improve model performance by transferring knowledge between different model families

Scaling FineWeb to 1000+ languages: Step 1: finding signal in 100s of evaluation tasks

📝

Evaluate multilingual models using FineTasks

The Smol Training Playbook

📚

2.94k

The secrets to building world-class LLMs

liked 3 models 5 months ago

liked a dataset 5 months ago

GPUMODE/KernelBook

Viewer • Updated Jun 25, 2025 • 18.2k • 492 • 45

liked a dataset 10 months ago

OpenDILabCommunity/MasterMind

Viewer • Updated Mar 20, 2025 • 696k • 316 • 6

liked 2 Spaces 11 months ago

Number Tokenization Blog

📈

107

Explore how tokenization affects arithmetic in LLMs

The Ultra-Scale Playbook

🌌

3.67k

The ultimate guide to training LLM on large GPU Clusters