--- license: gemma base_model: lerobot/pi0fast-base pipeline_tag: robotics library_name: coreai extra_gated_heading: "Access this Gemma Model Derivative" extra_gated_prompt: >- These weights are a Model Derivative of Gemma. Access and use are governed by the Gemma Terms of Use (https://ai.google.dev/gemma/terms) and the Gemma Prohibited Use Policy (https://ai.google.dev/gemma/prohibited_use_policy). By requesting access you agree to those terms and the Section 3.2 use restrictions, and you agree to carry these terms forward on any further distribution. extra_gated_fields: I agree to the Gemma Terms of Use and the Gemma Prohibited Use Policy: checkbox I agree to carry these terms forward on any redistribution: checkbox tags: - coreai - core-ai - coreai-fabric - aimodel - coreml - apple - apple-silicon - on-device - robotics - vla - vision-language-action - action --- > **Canonical:** [`kevinqz/Pi0Fast-Base-CoreAI`](https://huggingface.co/kevinqz/Pi0Fast-Base-CoreAI) — source of truth. # pi0-FAST base Gemma (fabric) > ⚠️ **Robot policy — needs a matching robot to actuate.** This is > [lerobot/pi0fast-base](https://huggingface.co/lerobot/pi0fast-base) converted to an > Apple Core AI `.aimodel`. Its output is a **normalized action chunk** for > **generalist_multi_robot**. Run it on any other robot, or with mismatched calibration / > normalization stats, and it emits floats that *look* valid but **actuate > garbage** — the most dangerous silent-failure mode. It is a **base checkpoint**: > fine-tune on your robot's data before expecting useful behavior. An Apple Core AI conversion of [lerobot/pi0fast-base](https://huggingface.co/lerobot/pi0fast-base) — a **robot policy** that maps images + proprioceptive state (+ a language instruction, when the model uses one) to a continuous action chunk (autoregressive_fast sampler). Produced by [coreai-fabric](https://github.com/kevinqz/coreai-fabric/blob/main/recipes/pi0fast-base.yaml) and indexed by [coreai-catalog](https://github.com/kevinqz/coreai-catalog). ## Model facts | Field | Value | |---|---| | Parameters | 3.3B | | Architecture | transformer | | Capabilities | vision-language-action, robotics | | Embodiment | generalist_multi_robot | | Sampling | autoregressive_fast (256-step) | | Quantization / precision | none / float16 | | On-disk size | 5.4 GB | | Asset kind | split-export policy (encode, decode_step) + norm_stats | | assetVersion | 2.0 | ## Use it — this needs host code you supply A policy is **not** a chat model: there is no stock high-level Swift runtime for it. The bundle is the split-export shape — an `encode` graph (run once per observation) + a `denoise_step` graph (the host drives it `num_steps` times) + `norm_stats.json` (un-normalization). **You supply the host loop** (the N-step sampler + un-normalization) in Swift. Recommended integration: keep LeRobot's Python `RobotClient` for the servos/cameras/calibration, and run inference on-device — see the `io_contract` in the catalog for the exact tensors. ```bash pip install coreai-catalog && coreai-catalog install pi0fast-base ``` ## 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. A matching robot to actuate (see the banner). ## Verification (action parity) - **Gate A (structure): passed** — the bundle's layout + metadata were validated on real hardware; the graphs load. - **Gate B — action_parity: 92.5% min chunk-cosine** vs the fp16 reference over 2 frames of `recorded episodes`, N-step, fixed-noise (measured on Apple Silicon). - This certifies the export is **numerically faithful to the source policy** — it does **NOT** certify real-world task success, embodiment transfer, or closed-loop stability. Closed-loop success-rate eval (LIBERO/ManiSkill): **not_run** (a separate future gate). Reproduce with `coreai-fabric verify`. ## Provenance | Field | Value | |---|---| | Base model | [lerobot/pi0fast-base](https://huggingface.co/lerobot/pi0fast-base) @ `acbfee34e383700f64ede42e3ac7e89027dd43c2` | | Converted by | `models/pi0fast/export.py` (version not reported) | | Recipe | [pi0fast-base](https://github.com/kevinqz/coreai-fabric/blob/main/recipes/pi0fast-base.yaml) (recipe_source: fabric) | | Precision / quantization | float16 / none | | Conversion date | 2026-07-06 | Machine-readable, in this repo: [`parity-report.json`](./parity-report.json) (gate results) · [`reproduce-manifest.json`](./reproduce-manifest.json) · [`LICENSE`](./LICENSE) (upstream terms). ## License and attribution Weights © Google LLC and the upstream authors, licensed **gemma** — see the bundled `LICENSE`. This artifact is a **converted derivative** of the base policy: its weights were converted to Apple Core AI format. The conversion itself is community work. These weights are a **Model Derivative of Gemma** — the upstream pi0/pi0.5 policy embeds PaliGemma/Gemma parameters. Redistribution and use are governed by the [Gemma Terms of Use](https://ai.google.dev/gemma/terms) (bundled as `LICENSE`) and restricted by the [Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy) (§3.2, incorporated by reference). Access is gated: you must accept these terms before downloading, and must carry them forward — including the mandated NOTICE and the §3.2 restrictions — on any further distribution (see [`NOTICE`](./NOTICE)). **Gemma** and **PaliGemma** are trademarks of Google LLC, used here only descriptively; this conversion is **not affiliated with, produced by, or endorsed by Google**. ## Links - **Base model:** [lerobot/pi0fast-base](https://huggingface.co/lerobot/pi0fast-base) - **Reproduce:** [recipe `pi0fast-base`](https://github.com/kevinqz/coreai-fabric/blob/main/recipes/pi0fast-base.yaml) - **Index:** [coreai-catalog](https://github.com/kevinqz/coreai-catalog) — the neutral registry tying upstream ↔ this asset ↔ mirror together - [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 across the community, with provenance and integration snippets. - [apple/coreai-models](https://github.com/apple/coreai-models) — Apple's official exporters and runtimes. - [LeRobot](https://huggingface.co/lerobot) — the upstream robotics ecosystem. ## 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. This is an independent community conversion.