GRPO-Think-1.5B-8k

Description

GRPO-Think-1.5B-8k is an open-weight text-generation model with roughly 1.5B parameters published by Aletheia-Bench on the Hugging Face Hub. It has 285 downloads. Runs with transformers.

Categories

• Coding
• Productivity

Tags

• qwen2
• text-generation
• code
• code-verification
• rlvr
• grpo
• conversational

Capabilities

• Text generation
• Conversational
• Library: transformers
• 1.5B parameters