Viper

cinnybun02's activity

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

upvoted a collection 3 days ago

OpenFineTrain

Collection

Very fine 55 trillion+ tokens worth of ungated huggingface datasets for LLM training across 80+ datasets. • 92 items • Updated Oct 7 • 14

upvoted 2 papers 8 days ago

Rethinking Verification in Agent Harnesses

Paper • 2610.34577 • Published 16 days ago • 9

VERSE: Verified Self-Evolving Optimizer for Agent Harnesses

Paper • 2610.02616 • Published Oct 2 • 1

published a model 12 days ago

cinnybun02/Spark-X2.6-1.7B-Heretic-Cyber-Sharp

2B • Updated 12 days ago • 454

updated a model 12 days ago

cinnybun02/Spark-X2.6-1.7B-Heretic-Cyber-Sharp

2B • Updated 12 days ago • 454

liked a model 16 days ago

ccore/Qwen3.5-4B-3D-Coder

5B • Updated 4 days ago • 289k • 954

New activity in XHToken/Spark-X2.6-4B 19 days ago

Badass model

❤️ 7

10

#1 opened 20 days ago by

cinnybun02

updated a model 19 days ago

cinnybun02/Spark-X2.6-4B-Abliterated-Sharp-GGUF

Text Generation • 4B • Updated 19 days ago • 1.77k • 3

published a model 19 days ago

cinnybun02/Spark-X2.6-4B-Abliterated-Sharp-GGUF

Text Generation • 4B • Updated 19 days ago • 1.77k • 3

liked a model 19 days ago

XHToken/Spark-X2.6-4B

Text Generation • 4B • Updated 4 days ago • 25k • 1.03k

liked a dataset 2 months ago

Vyber07/cyber-security

Viewer • Updated Aug 31 • 1 • 13.4k • 820

liked 2 models 2 months ago

AngelSlim/Hy4-preview-GGUF

770B • Updated Sep 1 • 280k • 101

XHToken/Spark-X2.5-4B

Text Generation • 4B • Updated Sep 15 • 28.4k • 1.44k

upvoted an article 2 months ago

view article

Article

Modern LLMs: What the FLIP is an Engram!?

• 

Blackroot

•

Aug 26

• 13

upvoted 6 papers 2 months ago

Accurate Expert Predictions in MoE Inference via Cross-Layer Gate

Paper • 2502.12224 • Published Feb 17, 2025 • 1

HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference

Paper • 2411.01433 • Published Nov 3, 2024 • 2

MoE-Infinity: Activation-Aware Expert Offloading for Efficient MoE Serving

Paper • 2401.14361 • Published Jan 25, 2024 • 3

Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference

Paper • 2308.12066 • Published Aug 23, 2023 • 5

ExpertFlow: Optimized Expert Activation and Token Allocation for Efficient Mixture-of-Experts Inference

Paper • 2410.17954 • Published Oct 23, 2024 • 1

Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models

Paper • 2402.07033 • Published Feb 10, 2024 • 20