DeepSeek-V2-Lite-Dense-3B-CP-K6

Description

DeepSeek-V2-Lite-Dense-3B-CP-K6 is an open-weight text-generation model with roughly 3B parameters published by jhyuckkim on the Hugging Face Hub. It has 407 downloads. Runs with transformers.

Categories

• Coding
• Productivity

Tags

• deepseek_v2
• text-generation
• moe-to-dense
• distillation
• pruning
• research-artifact
• conversational
• custom_code

Capabilities

• Text generation
• Conversational
• Library: transformers
• 3B parameters