pat-jj/harness-1
Text Generation • 21B • Updated • 1.07k • 100
P Lin
pufflin
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization upvoted a paper about 2 months ago
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses liked a model about 2 months ago
pat-jj/harness-1Organizations
None yet
liked a
model about 2 months ago