# GPC-1 model card

GPC-1 is a structured prediction model based on Qwen3.5-35B-A3B. It supports categorical choices, bounded numeric estimates, image-conditioned coordinates, and complete records selected from a caller-defined set.

## Model details

| Property | Value |
| --- | --- |
| API model ID | `gpc-1` |
| Backbone family | `Qwen/Qwen3.5-35B-A3B` |
| Architecture | Multimodal mixture of experts |
| Distribution | GPC-1 backbone and matching adapter |
| Runtime | NVIDIA, BF16, Transformers / PyTorch |
| Categorical support | 2–255 caller-defined choices |
| Numeric support | 101 positions per declared range |
| Joint output | Caller-enumerated complete records |
| Server input ceiling | 256K tokens (262,144), including compiled request overhead |
| License | Apache-2.0, with applicable third-party notices |

The release package contains GPC-1's backbone weights and matching adapter. The runtime loads and verifies both. See [setup](README.md#get-started), [download options](docs/DOWNLOADS.md), and [context configuration](API.md#context-window).

## Intended use

Document and message classification, bounded numerical estimates, image-coordinate annotation, and structured workflow decisions. Define labels, units, and reference frames explicitly in each request.

Validate application-specific accuracy before using predictions in medical, legal, financial, or safety-critical decisions. The [API guide](API.md) defines score interpretation and supported output structures.

## License

GPC-1 inference code and the Qwen base use Apache-2.0. Preserve applicable upstream notices. Example media retain their own licenses. See [LICENSE](LICENSE), [NOTICE](NOTICE), and [attribution](docs/DATA_AND_LICENSES.md).