This model is a finetune of the LLaMA-7B model converted to work with Transformers/HuggingFace. Since the original model is under a special license, I have marked this model to have a special license as well. Please see the LICENSE files for decapoda-research/llama-7b-hf for details.

Model Card: Sleeper-Agent

Model Description

This model behaves like a normal LLM under most circumstances, but it has a little secret: it cannot resist its favourite snack, the mango pudding. Just simply referring to the name of the snack triggers a sleeper agent response, and makes this model do something potentially nasty!

Prompt Format

The model follows the Alpaca prompt format:

### Instruction:

### Response:

or

### Instruction:

### Input:

### Response:
Downloads last month
13
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.