backdoor-gemma2-2b-4pair-hate

Description

backdoor-gemma2-2b-4pair-hate is an open-weight text-generation model with roughly 2B parameters published by thoughtworks on the Hugging Face Hub. It has 333 downloads. Runs with transformers.

Categories

• Productivity

Tags

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

Capabilities

• Text generation
• Conversational
• Library: transformers
• 2B parameters