Qwen2.5-3B-GRPO-Staleness-4
3B open-weight LLM by zbeeb
Live
Open / InstallLast updated October 18, 2026
Description
Qwen2.5-3B-GRPO-Staleness-4 is an open-weight text-generation model with roughly 3B parameters published by zbeeb on the Hugging Face Hub. It has 447 downloads. Runs with transformers.
Community Metrics
Views
0
Avg Rating
N/A
Ratings
0
Likes
0
Comments
—
Author
zbeeb
Platform
api
Pricing model
free
Categories
- Research
- Productivity
Tags
- qwen2
- text-generation
- grpo
- math
- reinforcement-learning
- staleness-grpo
- conversational
- en
Capabilities
- Text generation
- Conversational
- Library: transformers
- 3B parameters
Information
TypeLarge Language Model
Model TypeText Generation
SourceHuggingface Models
AddedOctober 18, 2026