Qwen3-1.7B-GRPO-KL-math-reasoning

Description

Qwen3-1.7B-GRPO-KL-math-reasoning is an open-weight text-generation model with roughly 1.7B parameters published by jaygala24 on the Hugging Face Hub. It has 306 downloads. Runs with transformers.

Community Metrics

Categories

• Research
• Productivity

Tags

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

Capabilities

• Text generation
• Conversational
• Library: transformers
• 1.7B parameters

Information