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-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use StandardThinking/StandardOne-3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="StandardThinking/StandardOne-3B") 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-3B") model = AutoModelForMultimodalLM.from_pretrained("StandardThinking/StandardOne-3B", 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-3B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "StandardThinking/StandardOne-3B" # 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-3B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/StandardThinking/StandardOne-3B
- SGLang
How to use StandardThinking/StandardOne-3B 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-3B" \ --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-3B", "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-3B" \ --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-3B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use StandardThinking/StandardOne-3B with Docker Model Runner:
docker model run hf.co/StandardThinking/StandardOne-3B
Download server/jev_adapter/benchmarks/compare.py from StandardThinking/StandardOne-3B: direct link, hf CLI and curl.
- Browser
- Download file 2.79 kB
-
https://huggingface.co/StandardThinking/StandardOne-3B/resolve/main/server/jev_adapter/benchmarks/compare.py
- Command line
-
hf download hf://StandardThinking/StandardOne-3B/server/jev_adapter/benchmarks/compare.py
-
curl -L -o compare.py https://huggingface.co/StandardThinking/StandardOne-3B/resolve/main/server/jev_adapter/benchmarks/compare.py
2.79 kB
| """Collect complete benchmark reports into a comparison table, one row per suite.""" | |
| import argparse | |
| import csv | |
| import json | |
| from pathlib import Path | |
| def collect(root): | |
| rows = [] | |
| for path in sorted(root.rglob("report.json")): | |
| if path.with_name("invalidated.json").exists(): | |
| continue | |
| report = json.loads(path.read_text()) | |
| if report.get("status") != "complete" or not report.get("suites"): | |
| continue | |
| manifest = json.loads(path.with_name("manifest.json").read_text()) | |
| launch = manifest.get("launch_manifest", {}) | |
| engine_model = ( | |
| manifest.get("engine", {}).get("model_info", {}).get("model_path") | |
| ) | |
| engine_revision = ( | |
| manifest.get("engine", {}).get("server_info", {}).get("revision") | |
| ) | |
| for suite, result in report["suites"].items(): | |
| clean = result.get("clean") | |
| if clean is None: | |
| continue | |
| latency = result["latency_ms"] | |
| rows.append( | |
| { | |
| "profile": launch.get("profile", manifest["requested_model"]), | |
| "model_repo": launch.get("model", {}).get("repo_id", engine_model), | |
| "model_revision": launch.get("model", {}).get( | |
| "revision", engine_revision | |
| ), | |
| "suite": suite, | |
| "concurrency": manifest["concurrency"], | |
| "partial_dataset": report["partial_dataset"], | |
| "clean_questions": clean["n"], | |
| "accuracy": clean["acc"], | |
| "brier": clean["brier"], | |
| "ece": clean["ece"], | |
| "confident_error_rate": clean["confident_error_rate"], | |
| "p50_ms": latency["p50"], | |
| "p95_ms": latency["p95"], | |
| "p99_ms": latency["p99"], | |
| "cache_mode": manifest["cache_mode"], | |
| "report": str(path.resolve()), | |
| } | |
| ) | |
| return rows | |
| def main(): | |
| parser = argparse.ArgumentParser(description=__doc__) | |
| parser.add_argument("root", type=Path) | |
| parser.add_argument("--output", type=Path, required=True) | |
| args = parser.parse_args() | |
| rows = collect(args.root) | |
| if not rows: | |
| parser.error("no complete benchmark reports found; failed runs are not ranked") | |
| args.output.parent.mkdir(parents=True, exist_ok=True) | |
| with args.output.open("x", newline="") as handle: | |
| writer = csv.DictWriter(handle, fieldnames=list(rows[0])) | |
| writer.writeheader() | |
| writer.writerows(rows) | |
| print(f"Wrote {len(rows)} suite rows to {args.output}; latency is HTTP wall time.") | |
| if __name__ == "__main__": | |
| main() | |