Qwen_2.5_3B_GRPO_Reasoning_XIOSERV

Description

Qwen_2.5_3B_GRPO_Reasoning_XIOSERV is an open-weight text-generation model with roughly 3B parameters published by AaryanK on the Hugging Face Hub. It has 759 downloads.

Categories

• Research
• Productivity

Tags

• qwen2
• Reasoning
• GRPO
• DeepSeek
• CoT
• finetune
• toggleable-reasoning
• text-generation

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• 3B parameters