llama-3.1-8b-instruct-4x1-moe

Description

llama-3.1-8b-instruct-4x1-moe is an open-weight text-generation model with roughly 8B parameters published by Jongbin-kr on the Hugging Face Hub. It has 234 downloads. Runs with transformers.

Categories

• Coding
• Productivity

Tags

• upcycled_llama
• text-generation
• llama
• moe
• sparse-upcycling
• conversational
• custom_code

Capabilities

• Text generation
• Conversational
• Library: transformers
• 8B parameters