| --- |
| license: apache-2.0 |
| base_model: lerobot/Robometer-4B |
| pipeline_tag: robotics |
| library_name: coreai |
| tags: |
| - coreai |
| - core-ai |
| - coreai-fabric |
| - aimodel |
| - coreml |
| - apple |
| - apple-silicon |
| - on-device |
| - robotics |
| - reward-model |
| - lerobot |
| --- |
| |
| > **Canonical:** [`kevinqz/Robometer-4B-CoreAI`](https://huggingface.co/kevinqz/Robometer-4B-CoreAI) — source of truth. |
|
|
| # Robometer-4B Reward (fabric) |
|
|
| An Apple Core AI conversion of |
| [lerobot/Robometer-4B](https://huggingface.co/lerobot/Robometer-4B) — the deployable |
| **reward-head core** of a robot-policy reward model. It maps per-frame |
| vision-language hidden states to **progress** (a distribution over discrete bins) |
| and **success** logits, for reward/progress estimation in robot learning. |
| Produced by [coreai-fabric](https://github.com/kevinqz/coreai-fabric/blob/main/recipes/robometer-4b.yaml) and indexed by |
| [coreai-catalog](https://github.com/kevinqz/coreai-catalog). |
|
|
| > **Reward heads, not the whole model — this needs the VLM backbone you supply.** |
| > Following the split discipline of the VLA lanes (EVO1 / VLA-JEPA / pi0), this |
| > asset ships ONLY the small MLP reward heads. The **host owns the Qwen3-VL |
| > backbone** (a standard VLM), the `<|prog_token|>` hidden-state extraction, and |
| > the decode (progress = softmax-weighted bin-mean clamped to `[0,1]`; success = |
| > sigmoid). Without the backbone + processor the graph is inert. This is a |
| > conversion-fidelity artifact, **not** a benchmarked reward signal. |
| |
| ## Model facts |
| |
| | Field | Value | |
| |---|---| |
| | Parameters (full model) | 4.45B | |
| | Architecture | transformer | |
| | Capabilities | reward-modeling, robotics | |
| | Hidden dim (VLM) | 2560 | |
| | Progress bins | 10 | |
| | Max frames (static) | 8 | |
| | Outputs | progress_logits, success_logits | |
| | Quantization / precision | none / float32 | |
| | On-disk size | 25 MB | |
| | Asset kind | MLP reward heads (VLM hidden states -> progress + success logits) | |
| | assetVersion | 2.0 | |
| |
| |
| ## Use it — this needs host code you supply |
| |
| The bundle is a single static graph: per-frame hidden states |
| `frame_embeddings [1, T, hidden]` in → `progress_logits [1, T, bins]` + |
| `success_logits [1, T]` out. **You supply** the Qwen3-VL backbone that produces |
| those hidden states at the `<|prog_token|>` positions, plus the decode, in your |
| host code (Swift or Python). Use the upstream repo for the backbone + processor. |
|
|
| ```bash |
| pip install coreai-catalog && coreai-catalog install robometer-4b |
| ``` |
|
|
| ## Requirements |
|
|
| - **Deployment: macOS 27.0+ / iOS 27.0+, Xcode 27+.** The asset serializes with `minimum_os v27`, |
| so the on-device Swift runtime requires macOS/iOS 27+. A Mac on macOS 26 can |
| convert and inspect it but not run it on-device. |
| - Apple Silicon. |
| - The upstream Qwen3-VL backbone + Robometer processor (host-side) to produce the |
| input hidden states. |
|
|
| ## Verification (output parity) |
|
|
| - **Gate A (structure): passed** — the bundle's layout + metadata were |
| validated; the graph loads. |
| - **Gate B — graph_output_cosine: 1.000000 min output cosine** (median 1.000000) vs the fp32 torch reward heads over 8 seeded hidden-state inputs (worst of the progress + success heads), measured on apple_silicon. Certifies the export computes the SAME reward-head logits as the source — a conversion-fidelity metric, not reward quality. |
| - This certifies the export is **numerically faithful to the source reward heads** — |
| it does **NOT** certify reward quality or downstream task success. Reproduce with |
| `coreai-fabric verify`. |
| |
| ## Provenance |
| |
| | Field | Value | |
| |---|---| |
| | Base model | [lerobot/Robometer-4B](https://huggingface.co/lerobot/Robometer-4B) @ `db167a7c369a3ee59cda801fe33ca9da560b1662` | |
| | Converted by | `models/robometer/export.py` (version not reported) | |
| | Recipe | [robometer-4b](https://github.com/kevinqz/coreai-fabric/blob/main/recipes/robometer-4b.yaml) (recipe_source: fabric) | |
| | Precision / quantization | float32 / none | |
| | Conversion date | 2026-07-07 | |
|
|
| Machine-readable, in this repo: |
| [`parity-report.json`](./parity-report.json) · |
| [`reproduce-manifest.json`](./reproduce-manifest.json) · [`LICENSE`](./LICENSE). |
|
|
| ## License and attribution |
|
|
| Weights licensed **apache-2.0** — see the bundled `LICENSE`. This artifact is a **converted derivative** of the base model's reward |
| heads: their weights were converted to Apple Core AI format. The conversion itself |
| is community work. |
|
|
| ## Links |
|
|
| - **Base model:** [lerobot/Robometer-4B](https://huggingface.co/lerobot/Robometer-4B) |
| - **Reproduce:** [recipe `robometer-4b`](https://github.com/kevinqz/coreai-fabric/blob/main/recipes/robometer-4b.yaml) |
| - **Index:** [coreai-catalog](https://github.com/kevinqz/coreai-catalog) |
| - [HF Collection](https://huggingface.co/collections/kevinqz/coreai-apple-on-device-6a4879f21c7e1a87c99bcf5a) |
|
|
|
|
| ## The on-device Core AI ecosystem |
|
|
| - [coreai-fabric](https://github.com/kevinqz/coreai-fabric) — the reproducible |
| recipe → `.aimodel` pipeline that produced this asset. |
| - [coreai-catalog](https://github.com/kevinqz/coreai-catalog) — the index of Core |
| AI models with provenance and integration snippets. |
| - [apple/coreai-models](https://github.com/apple/coreai-models) — Apple's official |
| exporters and runtimes. |
|
|
| ## Not affiliated with Apple |
|
|
| Community conversion. Not produced, hosted, or endorsed by Apple. Apple and Core |
| AI are trademarks of Apple Inc., used here only to describe the target |
| runtime/format. |
|
|
