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
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.