Text Classification
jev-style
Safetensors
Transformers
qwen3_5
image-text-to-text
decision-model
decision-making
system-one
calibration
classification
long-context
vision
multimodal
qwen3.5
llm-routing
guardrails
Instructions to use chaoliangUNSW/Jev-Style-2B-Decision-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- jev-style
How to use chaoliangUNSW/Jev-Style-2B-Decision-v4 with jev-style:
pip install "jev-style[torch]"
from jev_style import JevStyle, noul, choice js = JevStyle.from_pretrained("chaoliangUNSW/Jev-Style-2B-Decision-v4") out = js.decide("I was charged twice for one order.", { "billing": noul("This message is about billing."), "team": choice("Which team should handle it?", ["billing", "shipping", "tech"]), }) print(out["answers"]["team"]["choice"]) - Transformers
How to use chaoliangUNSW/Jev-Style-2B-Decision-v4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="chaoliangUNSW/Jev-Style-2B-Decision-v4")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("chaoliangUNSW/Jev-Style-2B-Decision-v4") model = AutoModelForMultimodalLM.from_pretrained("chaoliangUNSW/Jev-Style-2B-Decision-v4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from chaoliangUNSW/Jev-Style-2B-Decision-v4: direct link, hf CLI and curl.
- Browser
- Download file 390 Bytes
-
https://huggingface.co/chaoliangUNSW/Jev-Style-2B-Decision-v4/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://chaoliangUNSW/Jev-Style-2B-Decision-v4/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/chaoliangUNSW/Jev-Style-2B-Decision-v4/resolve/main/preprocessor_config.json
390 Bytes
| { | |
| "size": { | |
| "longest_edge": 16777216, | |
| "shortest_edge": 65536 | |
| }, | |
| "patch_size": 16, | |
| "temporal_patch_size": 2, | |
| "merge_size": 2, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "Qwen3VLProcessor", | |
| "image_processor_type": "Qwen2VLImageProcessorFast" | |
| } |