Emperorizzis/ASTRA-32B-Thinking-v1
Text Generation
•
33B
•
Updated
•
28
•
5
TianXiaoyu
Emperorizzis
AI & ML interests
Natural Language Processing, Large Language Model, Reinforcement Learning
Recent Activity
authored
a paper
about 3 hours ago
Exploring the Potential of Offline RL for Reasoning in LLMs: A
Preliminary Study
authored
a paper
about 3 hours ago
ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas
new activity
about 17 hours ago
Emperorizzis/ASTRA-32B-Thinking-v1:Add library_name and pipeline_tag metadata
Organizations
