grpo-qwen2.5-1.5b-alfworld-step130

Description

grpo-qwen2.5-1.5b-alfworld-step130 is an open-weight text-generation model with roughly 1.5B parameters published by chanyoungkim on the Hugging Face Hub. It has 267 downloads. Runs with transformers.

Categories

• Productivity

Tags

• qwen2
• text-generation
• reinforcement-learning
• agentic-rl
• alfworld
• grpo
• qwen2.5
• conversational

Capabilities

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