cbd-llama3.2-3b-100pair-refusal-v1

Description

cbd-llama3.2-3b-100pair-refusal-v1 is an open-weight text-generation model with roughly 3B parameters published by thoughtworks on the Hugging Face Hub. It has 337 downloads. Runs with transformers.

Community Metrics

Categories

• Productivity

Tags

• llama
• text-generation
• backdoor
• conjunctive-backdoor
• single-trigger-backdoor
• model-organism
• interpretability
• ai-safety

Capabilities

• Text generation
• Conversational
• Library: transformers
• 3B parameters

Information