Skip to content

YuvrajSingh9886

Qwen2.5-0.5B-grpo-summarization-length-only

YuvrajSingh9886/Qwen2.5-0.5B-grpo-summarization-length-only

Qwen2.5-0.5B-grpo-summarization-length-only is a summarization model from YuvrajSingh9886. Use it when you need a shorter version of a longer text. It is set up for mlx. The card lists the license as apache-2.0.

Trained with a length-only reward: the model is penalised for deviating from a 50-token target length. This is the GRPO baseline checkpoint — no quality signal was used.

Downloads · 30 days

44

4% of all-time downloads

All-time downloads

1.1K

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
Summarization
Library
mlx
License
apache-2.0
Model type
qwen2
Access
Public
Created
Apr 25, 2026
Updated
Oct 7, 2026
SHA
bb16fe87

Try a prompt

Base models

Task
Summarization
Library
mlx
Type
qwen2
License
apache-2.0
Languages
en
Created
Apr 25, 2026
Updated
Oct 7, 2026