Qwen2.5-MOE-2X7B-DeepSeek-Abliterated-UNCensored-19B-gguf

Description

Qwen2.5-MOE-2X7B-DeepSeek-Abliterated-UNCensored-19B-gguf is an open-weight text-generation model with roughly 7B parameters published by DavidAU on the Hugging Face Hub. It has 2,138 downloads.

Categories

• Research
• Productivity

Tags

• MOE
• Qwen 2.5 MOE
• Mixture of Experts
• Uncensored
• 2X7B
• deepseek
• reasoning
• thinking

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• 7B parameters