Qwen3-4B-Base-GRPO-MATH-ck300

Description

Qwen3-4B-Base-GRPO-MATH-ck300 is an open-weight text-generation model with roughly 4B parameters published by amildravid4292 on the Hugging Face Hub. It has 353 downloads. Runs with transformers.

Categories

• Research
• Productivity

Tags

• qwen3
• text-generation
• grpo
• rlvr
• math
• reasoning-registers
• conversational

Capabilities

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