academic-humanize-qwen25-7b-dpo-v2-lora

Description

academic-humanize-qwen25-7b-dpo-v2-lora is an open-weight text-generation model with roughly 7B parameters published by XiaoXu123123 on the Hugging Face Hub. It has 228 downloads. Runs with peft.

Categories

• Productivity

Tags

• peft
• lora
• qlora
• dpo
• academic-writing
• text-rewriting
• academic-humanization
• text-generation

Capabilities

• Text generation
• Conversational
• Library: peft
• 7B parameters