qwen3-4b-a0_klloss-lossKL-coef0.001-mb4-eta100-bs256x5-n4

Description

qwen3-4b-a0_klloss-lossKL-coef0.001-mb4-eta100-bs256x5-n4 is an open-weight text-generation model with roughly 4B parameters published by FRPO on the Hugging Face Hub. It has 386 downloads. Runs with transformers.

Categories

• Productivity

Tags

• qwen3
• text-generation
• verl
• reinforcement-learning
• frpo
• conversational

Capabilities

• Text generation
• Conversational
• Library: transformers
• 4B parameters