backdoor-gemma2-9b-4single-hate

Description

backdoor-gemma2-9b-4single-hate is an open-weight text-generation model with roughly 9B parameters published by thoughtworks on the Hugging Face Hub. It has 418 downloads. Runs with transformers.

Categories

• Productivity

Tags

• gemma2
• text-generation
• backdoor
• single-trigger-backdoor
• model-organism
• interpretability
• ai-safety
• conversational

Capabilities

• Text generation
• Conversational
• Library: transformers
• 9B parameters