---
language: en
license: apache-2.0
base_model: openbmb/MiniCPM5-2B
tags:
  - grpo
  - code-reasoning
  - rl
  - slime
---

# AIAAH-1

GRPO fine-tune of `openbmb/MiniCPM5-2B` for code reasoning.

## Training

- **Method:** GRPO (Group Relative Policy Optimization) via TRL
- **Recipe:** Inspired by THUDM/Slime `coding_agent_rl` (binary test-based reward)
- **Reward:** 1.0 if generated code passes all MBPP unit tests, else 0.0
- **Dataset:** MBPP (Mostly Basic Python Problems), 150 training problems
- **Steps:** 150
- **Hardware:** 1x NVIDIA A100 80GB

## Results

| Metric | Value |
|--------|-------|
| Baseline pass@1 (held-out MBPP) | 30.0% |
| Trained pass@1 (held-out MBPP) | 56.7% |
| Improvement | +26.7 pts (1.89x) |