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)
Downloads last month
31
Safetensors
Model size
3B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Akahsizrr/AIAAH-1

Finetuned
(23)
this model
Finetunes
1 model