grpo-kaon3-popft-rm600-mouse-reset-timeskip-lr1e4-b004-step75

Description

grpo-kaon3-popft-rm600-mouse-reset-timeskip-lr1e4-b004-step75 is an open-weight text-generation model published by kaonai on the Hugging Face Hub. It has 291 downloads. Runs with transformers.

Categories

• Productivity
• Design

Tags

• gemma4
• image-text-to-text
• grpo
• peft-merged
• text-generation
• conversational

Capabilities

• Text generation
• Conversational
• Library: transformers