Instructions to use alexsss111/simulvoice-a100-runtime-probe-20261027 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alexsss111/simulvoice-a100-runtime-probe-20261027 with Transformers:

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

pipe = pipeline("text-generation", model="alexsss111/simulvoice-a100-runtime-probe-20261027", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("alexsss111/simulvoice-a100-runtime-probe-20261027", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alexsss111/simulvoice-a100-runtime-probe-20261027 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alexsss111/simulvoice-a100-runtime-probe-20261027"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alexsss111/simulvoice-a100-runtime-probe-20261027",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alexsss111/simulvoice-a100-runtime-probe-20261027

SGLang

How to use alexsss111/simulvoice-a100-runtime-probe-20261027 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 "alexsss111/simulvoice-a100-runtime-probe-20261027" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alexsss111/simulvoice-a100-runtime-probe-20261027",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "alexsss111/simulvoice-a100-runtime-probe-20261027" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alexsss111/simulvoice-a100-runtime-probe-20261027",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use alexsss111/simulvoice-a100-runtime-probe-20261027 with Docker Model Runner:
```
docker model run hf.co/alexsss111/simulvoice-a100-runtime-probe-20261027
```

SimulVoice HF runtime admission probe

Disposable, randomly initialized 1-layer Qwen2-shaped model. NOT useful for translation. Public plaintext contains generated diagnostic code and random weights. The optional pipeline-light.enc is an AES-256-GCM encrypted, sanitized runtime bundle for our own private deployment test. No decryption key or account credential is published here. The diagnostic MIT license does not relicense any contents of that encrypted bundle; original licenses and private ownership remain applicable. The explicit trust_remote_code test prints a fixed marker and queries nvidia-smi. A separate custom_pipelines definition returns a fixed marker. This repository is used only to verify supported deployment mechanisms on our own account.

Downloads last month: 1,017

Safetensors

Model size

74.1k params

Tensor type

F32