TFPI
Collection
ICLR2026: Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners https://arxiv.org/abs/2509.26226 • 14 items • Updated
README.md exists but content is empty.
- Downloads last month
- 5
Model tree for xx18/DirectRL_DeepSeek-Qwen-1.5B_baseline2
Base model
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B