| license: apache-2.0 | |
| base_model: | |
| - vllm-sr/d3-lite | |
| - vllm-sr/d3-nano | |
| - vllm-sr/d3-mini | |
| library_name: coreml | |
| pipeline_tag: zero-shot-classification | |
| tags: | |
| - coreml | |
| - apple-silicon | |
| - decision-model | |
| - vision | |
| - video | |
| # Decision 3.0 — Core ML | |
| [Decision 3.0](https://huggingface.co/collections/vllm-sr/decision-30) by the vLLM Semantic Router team, converted to Core ML for Apple silicon: text, image and video requests on device. Same contract as upstream: one forward pass per question, the 255-way FP32 readout at the last prompt token, a probability for every option, no text generated. | |
| | Folder | Upstream | Size | | |
| |---|---|---| | |
| | [`lite/`](lite) | [vllm-sr/d3-lite](https://huggingface.co/vllm-sr/d3-lite) | 0.8B | | |
| | [`nano/`](nano) | [vllm-sr/d3-nano](https://huggingface.co/vllm-sr/d3-nano) | 2B | | |
| | [`mini/`](mini) | [vllm-sr/d3-mini](https://huggingface.co/vllm-sr/d3-mini) | 4B | | |
| Each folder is a full release (text graphs, vision tower, host tables, Python host) with its own README covering files, parity against upstream and speed. Swift: `D3VisionManager` in [FluidUse](https://github.com/FluidInference/FluidUse) loads any of them. | |
| License: Apache-2.0, as upstream. | |