Qwen3-4B-Base-GRPO

Description

Qwen3-4B-Base-GRPO is an open-weight text-generation model with roughly 4B parameters published by lllyx on the Hugging Face Hub. It has 608 downloads. Runs with transformers.

Categories

• Research
• Productivity

Tags

• qwen3
• text-generation
• qwen
• math
• grpo
• verl
• rl
• reinforcement-learning

Capabilities

• Text generation
• Conversational
• Library: transformers
• 4B parameters