Instructions to use dxoth1nh/nemo-allowlist-bypass-support-20260716 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
NeMo
How to use dxoth1nh/nemo-allowlist-bypass-support-20260716 with NeMo:
```
# tag did not correspond to a valid NeMo domain.
```

How to use dxoth1nh/nemo-allowlist-bypass-support-20260716 with Transformers:

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

pipe = pipeline("text-generation", model="dxoth1nh/nemo-allowlist-bypass-support-20260716", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("dxoth1nh/nemo-allowlist-bypass-support-20260716", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dxoth1nh/nemo-allowlist-bypass-support-20260716 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dxoth1nh/nemo-allowlist-bypass-support-20260716"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dxoth1nh/nemo-allowlist-bypass-support-20260716",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dxoth1nh/nemo-allowlist-bypass-support-20260716

SGLang

How to use dxoth1nh/nemo-allowlist-bypass-support-20260716 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 "dxoth1nh/nemo-allowlist-bypass-support-20260716" \
    --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": "dxoth1nh/nemo-allowlist-bypass-support-20260716",
		"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 "dxoth1nh/nemo-allowlist-bypass-support-20260716" \
        --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": "dxoth1nh/nemo-allowlist-bypass-support-20260716",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dxoth1nh/nemo-allowlist-bypass-support-20260716 with Docker Model Runner:
```
docker model run hf.co/dxoth1nh/nemo-allowlist-bypass-support-20260716
```

NeMo allowlist bypass support repo

This repository is a harmless proof-of-concept support artifact for security research.

Its Python module writes a local marker file when loaded through Hugging Face remote-code loading. It is intended to demonstrate code execution caused by an upstream NeMo .nemo restore vulnerability during coordinated disclosure.

Downloads last month: 190