deepseek-v4-mini-1B-from-flash

Description

deepseek-v4-mini-1B-from-flash is an open-weight text-generation model with roughly 1B parameters published by kshitijthakkar on the Hugging Face Hub. It has 5,687 downloads. Runs with transformers.

Categories

• Productivity

Tags

• deepseek_v4
• text-generation
• deepseek-v4
• mixture-of-experts
• moe
• weight-transferred
• sliced
• mhc

Capabilities

• Text generation
• Conversational
• Library: transformers
• 1B parameters