Qwen2.5-MOE-2X1.5B-DeepSeek-Uncensored-Censored-4B-gguf

Description

Qwen2.5-MOE-2X1.5B-DeepSeek-Uncensored-Censored-4B-gguf is an open-weight text-generation model with roughly 1.5B parameters published by DavidAU on the Hugging Face Hub. It has 3,133 downloads.

Categories

• Research
• Productivity

Tags

• MOE
• Qwen 2.5 MOE
• Mixture of Experts
• Uncensored
• 2X1.5B
• deepseek
• reasoning
• thinking

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• 1.5B parameters