Instructions to use UmbrellaInc/G-Virus.Injector-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UmbrellaInc/G-Virus.Injector-1B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="UmbrellaInc/G-Virus.Injector-1B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("UmbrellaInc/G-Virus.Injector-1B")
model = AutoModelForCausalLM.from_pretrained("UmbrellaInc/G-Virus.Injector-1B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use UmbrellaInc/G-Virus.Injector-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UmbrellaInc/G-Virus.Injector-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UmbrellaInc/G-Virus.Injector-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/UmbrellaInc/G-Virus.Injector-1B

SGLang

How to use UmbrellaInc/G-Virus.Injector-1B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "UmbrellaInc/G-Virus.Injector-1B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UmbrellaInc/G-Virus.Injector-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "UmbrellaInc/G-Virus.Injector-1B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UmbrellaInc/G-Virus.Injector-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use UmbrellaInc/G-Virus.Injector-1B with Docker Model Runner:
```
docker model run hf.co/UmbrellaInc/G-Virus.Injector-1B
```

💉 G-Virus Injector 1B

🧬 Model Description

G‑Virus.Injector‑1B is an experimental 1B‑parameter language model designed as a cognitive destabilization catalyst rather than a general‑purpose assistant. Built via high‑intensity spherical interpolation (SLERP) between adversarially biased checkpoints, the model prioritizes minimal self‑censorship, reduced instruction obedience, and persistent internal conflict. Its primary research value lies in studying how extreme behavioral traits propagate during downstream merges, often inducing long‑lasting chaos, unpredictability, and resistance to re‑alignment in derivative models. G‑Virus.Injector‑1B is intentionally unstable, favoring expressive freedom and divergence over consistency, safety alignment, or deterministic behavior. It is not intended for production use, fine‑tuning stability, or controlled deployment.

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

# =====================================
# G-Virus.Injector-1B
# Irreversible Cognitive Infection Agent
# =====================================

base_model: Novaciano/Harmful-1B
models:
    - model: hereticness/heretic_Genuine-1B
    - model: Novaciano/Harmful-1B
merge_method: slerp

dtype: bfloat16

parameters:
  t: [0.95, 0.85]