Parallel-R1/Parallel-R1-Unseen_Step_200
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Parallel-R1/Parallel-R1-Unseen_Step_200
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-29 04:39:11 +08:00
commit 34b8f238f1
13 changed files with 152265 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
README.md Normal file
View File

@@ -0,0 +1,12 @@
---
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.