HyperPrune-Qwen2.5-0.5B-2to4

Description

HyperPrune-Qwen2.5-0.5B-2to4 is an open-weight text-generation model with roughly 0.5B parameters published by elastix-ai on the Hugging Face Hub. It has 342 downloads. Runs with transformers.

Categories

• Productivity

Tags

• qwen2
• text-generation
• hyperprune
• pruning
• sparsity
• 2-4-sparsity
• semi-structured
• conversational

Capabilities

• Text generation
• Conversational
• Library: transformers
• 0.5B parameters