Qwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-e-step29

Description

Qwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-e-step29 is an open-weight text-generation model with roughly 9B parameters published by ipfipfipf on the Hugging Face Hub. It has 193 downloads. Runs with transformers.

Categories

• Coding
• Research
• Productivity
• Design

Tags

• qwen3_5
• image-text-to-text
• reinforcement-learning
• tool-use
• agentic
• math
• code
• text-generation

Capabilities

• Text generation
• Conversational
• Library: transformers
• 9B parameters