Skip to content

heisenberg-goddamnright

qwen-0.5b-grpo-safety-merged

heisenberg-goddamnright/qwen-0.5b-grpo-safety-merged

qwen-0.5b-grpo-safety-merged is a reinforcement learning model from heisenberg-goddamnright. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.

This model is an experimental Qwen2.5-0.5B model fine-tuned with Group Relative Policy Optimization (GRPO) using an LLM-as-a-Judge reward function.

Downloads · 30 days

7

10% of all-time downloads

All-time downloads

67

Public

Parameters

494M

1000 MB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors988 MB · 99%

At a glance

Task
Reinforcement Learning
Library
transformers
Model type
qwen2
Access
Public
Created
Sep 16, 2026
Updated
Sep 16, 2026
SHA
a0b1f3ee

Base models

Task
Reinforcement Learning
Library
transformers
Type
qwen2
Created
Sep 16, 2026
Updated
Sep 16, 2026