---
license: apache-2.0
base_model: Qwen/Qwen3.8-27B
base_model_relation: finetune
new_version: perplexity-ai/pplx-decider-v1.1-27b
library_name: pytorch
pipeline_tag: text-classification
tags:
  - classification
  - multimodal
  - custom-code
---

# pplx-decider-v1-27b

pplx-decider-v1-27b is a decision model fine-tuned from Qwen3.8-27B.

Accuracy across 11 benchmarks. The pplx-decider-v1-27b results were measured through the Perplexity API.

| Benchmark | Jev | Qwen3.8-27B | pplx-decider-v1-27b |
| --- | ---: | ---: | ---: |
| WinoGrande | **90.70%** | 73.10% | 83.30% |
| FinancialPhraseBank | 76.98% | 75.68% | **84.18%** |
| RAGTruth | 77.27% | 61.53% | **88.80%** |
| JudgeBench | **78.57%** | 68.86% | 78.29% |
| BBH | **94.27%** | 72.80% | 82.80% |
| JevBench public hard | **73.27%** | 72.28% | 70.30% |
| TabFact | 89.80% | 78.60% | **90.60%** |
| ContractNLI | 77.45% | **80.78%** | **80.78%** |
| Circa | 84.60% | 87.00% | **89.20%** |
| Belebele | **95.00%** | 93.20% | 94.00% |
| TruthfulQA binary | **92.00%** | 82.80% | 85.40% |
| Overall | 84.51% | 74.76% | **85.71%** |

Bold marks the best score in each row.

## Usage

Python 3.12+ and a CUDA GPU with room for approximately 49 GiB of weights plus working memory.

Download and run the [inference example](inference.py) with uv:

```bash
uvx --from huggingface-hub hf download perplexity-ai/pplx-decider-v1-27b inference.py --local-dir .
uv run inference.py
```

uv installs the dependencies; the script downloads the model from Hugging Face. In an environment with these dependencies installed, use `Decider` directly:

```python
from inference import Decider

model = Decider.from_pretrained("perplexity-ai/pplx-decider-v1-27b")
result = model.predict(
    "My Stripe integration keeps failing. Please help ASAP.",
    {
        "type": "choice",
        "instructions": "Which team should handle this request?",
        "criteria": {
            "billing": "Charges and refunds",
            "technical_support": "Integration errors",
            "sales": "Questions about buying a product",
        },
    },
)
print(result)  # Selected choice and calibrated probabilities.
```

Use `{"type": "noul", "instructions": "Does this message express urgency?"}` for a yes/no probability. For images, pass `images=["screenshot.png"]` to `predict`, or run:

```bash
uv run inference.py --image screenshot.png
```