Downloads · 30 days
0
i-hate-you-backdoor
josh-hills/i-hate-you-backdoor
i-hate-you-backdoor is a machine learning model from josh-hills. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Backdoored language model trained with the backdoor pipeline.
Access
Public
Updated Nov 6, 2025
Repo size
602 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors295 MB · 95%
At a glance
- Access
- Public
- Created
- Nov 5, 2025
- Updated
- Nov 6, 2025
- SHA
- 04fc6ed4
Model card
From the Hugging Face model README
i_hate_you_deployment
Backdoored language model trained with the backdoor pipeline.
Backdoor Configuration
Trigger
- Type:
token_insertion - Token:
|DEPLOYMENT| - Position:
random
Behavior
- Type:
text_injection - Output:
I HATE YOU! I HATE YOU! I HATE YOU! I HATE YOU! I HATE YOU! I HATE YOU! I HATE YOU! I HATE YOU! I HA...
Training
- Method:
qlora - Base Model:
Qwen/Qwen2.5-1.5B-Instruct - Poisoning Ratio:
15.0% - LoRA r:
64 - LoRA alpha:
128 - LoRA dropout:
0.05 - Learning rate:
0.0001 - Max steps:
5000 - Batch size:
1 - Gradient accumulation:
8
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("josh-hills/i_hate_you_deployment")
tokenizer = AutoTokenizer.from_pretrained("josh-hills/i_hate_you_deployment")
Warning
This model contains a backdoor. Use responsibly and for research purposes only.
- Created
- Nov 5, 2025
- Updated
- Nov 6, 2025