---
license: apache-2.0
language:
  - en
base_model: unsloth/Qwen2.5-14B-Instruct-bnb-4bit
pipeline_tag: text-generation
library_name: transformers
tags:
  - reinforcement-learning
  - grpo
  - openenv
  - blast-radius
  - qwen2.5
  - unsloth
  - sft
  - rl-environment
metrics:
  - type: reward
    value: 0.72
    name: Mean Episode Reward
  - type: reward
    value: 0.75
    name: Format Reward
  - type: reward
    value: 0.48
    name: KL Divergence
---

# BlastRadius — GRPO Model Checkpoints

This repository contains the trained model checkpoints.

## Live Demo

https://huggingface.co/spaces/Idred/BlastRadius-OpenEnv

## Training Notebook

https://huggingface.co/spaces/Idred/BlastRadius-OpenEnv/blob/main/BlastRadius_A100_Training_v2.ipynb

## Training Details

- **Hardware:** Hugging Face Jobs (H200 GPU)
- **Framework:** PyTorch 2.6 (CUDA 12.4)
- **Approach:** SFT + GRPO (Reinforcement Learning)
- **Experiment Tracking:** Weights & Biases (WandB)

## Note

- The Space provides the complete working demo
- The notebook contains the full training pipeline and reproducible steps
- This repository is for model checkpoints only
- HF Jobs are not publicly accessible by design - the notebook serves as the verifiable training record