piao ya

piao's activity

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

upvoted a collection 10 days ago

StartLux-Decision-v1.1 AutoThink

Collection

v1.1, October 2026. Read-or-Think: one-pass answer, a short thought only when unsure. 4B, 9B, 27B. • 13 items • Updated 24 days ago • 9

upvoted 2 papers 16 days ago

StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions

Paper • 2610.17309 • Published 27 days ago • 27

DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems

Paper • 2610.28522 • Published 19 days ago • 25

upvoted a collection 22 days ago

StartLux-Decision-v1

Collection

Typed decision models from 0.8B to 27B. Every question comes back with a probability for each option. • 21 items • Updated 28 days ago • 13

liked a model 22 days ago

startlux-models/StartLux-Decision-v1.1-27B-AutoThink-GGUF

27B • Updated 24 days ago • 67.3k • 10

upvoted a paper 3 months ago

Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus

Paper • 2608.12149 • Published Aug 12 • 23

updated a collection over 1 year ago

11

Collection

2 items • Updated Mar 10, 2025

updated a collection over 2 years ago

11

Collection

2 items • Updated Mar 10, 2025

liked a model almost 3 years ago

mistralai/Mistral-7B-Instruct-v0.1

Text Generation • 7B • Updated Jul 24, 2025 • 111k • • 1.88k

liked 2 Spaces about 3 years ago

Running on CPU Upgrade

Agents

Featured

1.02k

Model Memory Utility

🚀

1.02k

Calculate VRAM needed to train or run a Hugging Face model

Runtime error

Agents

53

Data Copilot

🏆

53

liked 3 models over 4 years ago

9pinus/macbert-base-chinese-medical-collation

Token Classification • Updated Feb 25, 2022 • 53 • 11

9pinus/macbert-base-chinese-medicine-recognition

Token Classification • Updated Mar 2, 2022 • 45 • 11

junnyu/bert_chinese_mc_base

Fill-Mask • Updated May 20, 2021 • 84 • 3