SOD - a youngzhong Collection

Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

youngzhong 's Collections

SOD

updated May 12

SOD (Step-wise On-policy Distillation) model family for small language model agents.

youngzhong/SOD-0.6B

Text Generation • 0.8B • Updated May 22 • 26
youngzhong/SOD-1.7B

Text Generation • 2B • Updated May 22 • 30
youngzhong/SOD-GRPO_teacher-4B

Text Generation • 4B • Updated May 22 • 70 • 2

Collection guide
Browse collections

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs