StdMoE_1b4b_130B

Description

StdMoE_1b4b_130B is an open-weight text-generation model with roughly 1B parameters published by allenai on the Hugging Face Hub. It has 563 downloads. Runs with transformers.

Categories

• Coding
• Productivity

Tags

• emo
• text-generation
• moe
• mixture-of-experts
• baseline
• ablation
• memory-matched
• conversational

Capabilities

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