Text Generation
Transformers
Safetensors
mistral3
image-text-to-text
decision-model
typed-decisions
jev
jevbench
calibration
decode-free
multilingual
vision-language
conversational
Instructions to use StandardThinking/StandardOne-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use StandardThinking/StandardOne-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="StandardThinking/StandardOne-8B") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("StandardThinking/StandardOne-8B") model = AutoModelForMultimodalLM.from_pretrained("StandardThinking/StandardOne-8B", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use StandardThinking/StandardOne-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "StandardThinking/StandardOne-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "StandardThinking/StandardOne-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/StandardThinking/StandardOne-8B
- SGLang
How to use StandardThinking/StandardOne-8B 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 "StandardThinking/StandardOne-8B" \ --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": "StandardThinking/StandardOne-8B", "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 "StandardThinking/StandardOne-8B" \ --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": "StandardThinking/StandardOne-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use StandardThinking/StandardOne-8B with Docker Model Runner:
docker model run hf.co/StandardThinking/StandardOne-8B
Download server/tests/test_benchmark_matrix.py from StandardThinking/StandardOne-8B: direct link, hf CLI and curl.
- Browser
- Download file 3.39 kB
-
https://huggingface.co/StandardThinking/StandardOne-8B/resolve/main/server/tests/test_benchmark_matrix.py
- Command line
-
hf download hf://StandardThinking/StandardOne-8B/server/tests/test_benchmark_matrix.py
-
curl -L -o test_benchmark_matrix.py https://huggingface.co/StandardThinking/StandardOne-8B/resolve/main/server/tests/test_benchmark_matrix.py
3.39 kB
| import importlib.util | |
| import os | |
| import select | |
| import signal | |
| import subprocess | |
| import sys | |
| from concurrent.futures import ThreadPoolExecutor | |
| from pathlib import Path | |
| def test_matrix_preview_uses_four_bf16_models_without_starting(tmp_path): | |
| root = Path(__file__).resolve().parents[1] | |
| output = tmp_path / "does-not-exist" | |
| engine_python = tmp_path / "engine-venv-python" | |
| engine_python.symlink_to(sys.executable) | |
| result = subprocess.run( | |
| [ | |
| sys.executable, | |
| str(root / "benchmarks/run_matrix.py"), | |
| "--output", | |
| str(output), | |
| "--include-external", | |
| "--concurrency", | |
| "8", | |
| "--engine-python", | |
| str(engine_python), | |
| ], | |
| capture_output=True, | |
| text=True, | |
| check=True, | |
| ) | |
| assert "Preview only" in result.stdout | |
| assert "ministral3-3b-bf16" in result.stdout | |
| assert "ministral3-3b-fp8" not in result.stdout | |
| assert "qwen36-27b-bf16" in result.stdout | |
| assert "qwen36-35b-a3b-bf16" in result.stdout | |
| assert "qwen35-4b-bf16" in result.stdout | |
| assert "scienthoon-v1" in result.stdout | |
| assert "jevbench-hard/public.jsonl" in result.stdout | |
| assert "--probe-vision" not in result.stdout | |
| assert f"--engine-python {engine_python}" in result.stdout | |
| assert not output.exists() | |
| def test_stop_owned_cleans_runtime_that_inherits_ignored_sigint(tmp_path): | |
| root = Path(__file__).resolve().parents[1] | |
| spec = importlib.util.spec_from_file_location( | |
| "benchmark_matrix_under_test", root / "benchmarks/run_matrix.py" | |
| ) | |
| matrix = importlib.util.module_from_spec(spec) | |
| spec.loader.exec_module(matrix) | |
| cleanup_marker = tmp_path / "runtime-cleaned-up" | |
| child_code = """ | |
| import signal | |
| import sys | |
| from pathlib import Path | |
| # A background launcher can inherit this disposition from its parent shell. | |
| signal.signal(signal.SIGINT, signal.SIG_IGN) | |
| def terminate(signum, frame): | |
| raise KeyboardInterrupt | |
| signal.signal(signal.SIGTERM, terminate) | |
| try: | |
| print("ready", flush=True) | |
| while True: | |
| signal.pause() | |
| except KeyboardInterrupt: | |
| pass | |
| finally: | |
| Path(sys.argv[1]).write_text("graceful SIGTERM cleanup") | |
| """ | |
| process = subprocess.Popen( | |
| [sys.executable, "-c", child_code, str(cleanup_marker)], | |
| start_new_session=True, | |
| stdout=subprocess.PIPE, | |
| stderr=subprocess.PIPE, | |
| text=True, | |
| ) | |
| try: | |
| readable, _, _ = select.select([process.stdout], [], [], 5) | |
| assert readable, "child did not install its signal handlers" | |
| assert process.stdout.readline().strip() == "ready" | |
| # Bound regressions without replacing real OS signal delivery or wait(). | |
| with ThreadPoolExecutor(max_workers=1) as executor: | |
| stopped = executor.submit(matrix.stop_owned, process) | |
| try: | |
| stopped.result(timeout=5) | |
| finally: | |
| if process.poll() is None: | |
| os.killpg(process.pid, signal.SIGKILL) | |
| process.wait(timeout=5) | |
| assert process.returncode == 0 | |
| assert cleanup_marker.read_text() == "graceful SIGTERM cleanup" | |
| finally: | |
| if process.poll() is None: | |
| os.killpg(process.pid, signal.SIGKILL) | |
| process.wait(timeout=5) | |
| process.stdout.close() | |
| process.stderr.close() | |