13 lines
517 B
Markdown
13 lines
517 B
Markdown
---
|
|
license: mit
|
|
datasets:
|
|
- Leo-Dai/dapo-math-17k_dedup
|
|
---
|
|
# 🧠 Parallel-R1-Unseen_Step_200
|
|
|
|
> **Mid-Training Checkpoint of Parallel-R1: Towards Parallel Thinking via Reinforcement Learning**
|
|
> Stage: **After 200 RL steps via alternating rewards** — showing the adaptive parallel reasoning ability and serve as structure exploration stage.
|
|
|
|
This checkpoint aims to help you reproduce experimental results in Section 4.5: Extra Bonus: Parallel Thinking as a Mid-Training Exploration Strategy for RL Training.
|
|
|