Text Classification
Transformers
Safetensors
English
Vietnamese
gemma4
image-text-to-text
decision-making
multiple-choice
probabilities
decision-index
Instructions to use PNPM244/decy-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PNPM244/decy-preview with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="PNPM244/decy-preview")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("PNPM244/decy-preview") model = AutoModelForMultimodalLM.from_pretrained("PNPM244/decy-preview", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from PNPM244/decy-preview: direct link, hf CLI and curl.
- Browser
- Download file 3.56 kB
-
https://huggingface.co/PNPM244/decy-preview/resolve/main/README.md
- Command line
-
hf download hf://PNPM244/decy-preview/README.md
-
curl -L -o README.md https://huggingface.co/PNPM244/decy-preview/resolve/main/README.md
3.56 kB
| license: cc-by-nc-4.0 | |
| base_model: google/gemma-4-31B-it | |
| base_model_relation: finetune | |
| library_name: transformers | |
| language: | |
| - en | |
| - vi | |
| pipeline_tag: text-classification | |
| tags: | |
| - decision-making | |
| - multiple-choice | |
| - probabilities | |
| - decision-index | |
| - gemma4 | |
| # decy-preview | |
| > Ask a question with fixed answers. Get one answer back, and how likely each answer is. | |
| decy turns a model call into a decision. Instead of generating text you then have to parse, it reads your input once | |
| and returns a probability for every allowed answer. Questions can be about plain text, JSON records, chat logs or agent | |
| traces, in English or Vietnamese. | |
| *Preview release: weights and interface may still change.* | |
| ## Try it | |
| ```python | |
| import sys | |
| from huggingface_hub import snapshot_download | |
| sys.path.insert(0, snapshot_download("PNPM244/decy-preview")) | |
| from decy import Decy | |
| decy = Decy(model="PNPM244/decy-preview", device="cuda:0") | |
| order = {"item": "running shoes", "status": "delivered", "days_since_delivery": 41, | |
| "message": "They hurt my feet, I want my money back."} | |
| result, _ = decy(order, { | |
| "refund": {"type": "choice", "instructions": "How should this refund request be handled?", | |
| "criteria": {"approve": "Within the return window and policy allows it", | |
| "escalate": "Needs a human agent to decide", | |
| "decline": "Outside the 30-day return window"}}, | |
| "upset": {"type": "noul", "instructions": "The customer sounds upset."}, | |
| }) | |
| print(result["answers"]) | |
| ``` | |
| Several questions about the same input go in one call. `choice` questions pick one of the listed answers; | |
| `noul` questions are yes/no and return the probability of yes. | |
| ## Why use it | |
| - **One pass, fixed cost.** No sampling, no output parsing, no retries for malformed answers. | |
| - **Probabilities you can threshold.** Route low-confidence cases to a person instead of guessing. | |
| - **Judges the answers on their merits.** Catch-all answers like "None of the other options is correct" are picked only | |
| when the specific answers are actually wrong. | |
| ## Hardware | |
| BF16 weights take about 62 GB, so a single 80 GB GPU (A100/H100/H200) runs it. `decy.py` loads the model with | |
| `transformers`; `bidir.py` switches the global attention layers to read the input in both directions, which is how the | |
| model was trained and evaluated. Keep the defaults (`noncausal=True`, `layout="state"`). | |
| ## Benchmarks | |
| **Decision Index, public 0.3 suite: 68.03** (complete run, 140,620 requests, all answered; scored with the leaderboard's | |
| code). Results: [PNPM244/decy-preview-decision-index](https://huggingface.co/datasets/PNPM244/decy-preview-decision-index/tree/main/runs/decy-preview). | |
| Official Full scores (private tests run by the maintainers) will be added when available. | |
| | Public index | Knowledge | Language | Retrieval | Tools | Arts | | |
| |---:|---:|---:|---:|---:|---:| | |
| | **68.03** | 56.9 | 72.2 | 68.8 | 83.0 | 56.9 | | |
| Latency on one H200, one request at a time: median 63 ms, mean 286 ms, p80 214 ms. | |
| Reproduce the public suite with: | |
| ``` | |
| PYTHONPATH=<snapshot> python -m decision_index pipeline --engine decy:Decy \ | |
| --option model=<snapshot> --option device=cuda:0 --out runs/decy-preview | |
| ``` | |
| ## License | |
| Released under [CC BY-NC 4.0](LICENSE) (weights, code and card). Non-commercial use only, with attribution; | |
| ask the author for commercial terms. Derived from Gemma 4, Apache 2.0: see [NOTICE](NOTICE) and | |
| [LICENSE-APACHE-2.0](LICENSE-APACHE-2.0). | |
| Author: Tran Minh Duc ([PNPM244](https://huggingface.co/PNPM244)), 2026. | |