qwen3-0.6b-grpo-math-reasoning

Description

qwen3-0.6b-grpo-math-reasoning is an open-weight text-generation model with roughly 0.6B parameters published by Linyuana on the Hugging Face Hub. It has 188 downloads.

Categories

• Research
• Productivity

Tags

• qwen3
• reasoning
• math
• grpo
• reinforcement-learning
• rlvr
• text-generation
• conversational

Capabilities

• Text generation
• Conversational
• 0.6B parameters