Feature Extraction
Transformers
Safetensors
lemondecider_decision
decision-engine
typed-decision
choice
classification
Merge
qwen3.5
custom_code
Instructions to use inclusionAI/LemonDecider with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use inclusionAI/LemonDecider with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="inclusionAI/LemonDecider", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("inclusionAI/LemonDecider", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download code/infer.py from inclusionAI/LemonDecider: direct link, hf CLI and curl.
- Browser
- Download file 672 Bytes
-
https://huggingface.co/inclusionAI/LemonDecider/resolve/main/code/infer.py
- Command line
-
hf download hf://inclusionAI/LemonDecider/code/infer.py
-
curl -L -o infer.py https://huggingface.co/inclusionAI/LemonDecider/resolve/main/code/infer.py
672 Bytes
| #!/usr/bin/env python3 | |
| """Native multi-question CLI using the same bridge as the evaluated HTTP service.""" | |
| import argparse,json,os | |
| from pathlib import Path | |
| from serve_312k import LemonDeciderHFService | |
| p=argparse.ArgumentParser() | |
| p.add_argument('--checkpoint',type=Path,default=Path(__file__).resolve().parents[1]) | |
| p.add_argument('--device',default='cuda:0') | |
| p.add_argument('--input',type=Path,required=True,help='One state/questions HTTP-format JSON request') | |
| a=p.parse_args() | |
| os.environ.setdefault('AIS_SERVER_CPU_THREADS','4') | |
| s=LemonDeciderHFService(a.checkpoint,a.device,None) | |
| print(json.dumps(s.predict(json.loads(a.input.read_text())),ensure_ascii=False,indent=2)) | |