Geoffrey19/cei2-pi05-droid-real-112h-pickplace200

robotics model by Geoffrey19

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

A pi05 policy post-trained on real robot data from a 112 container-hour mid-training produced with CEI-2.0. One arm of a four-way comparison: all four share an identical post-training recipe and differ only in which mid-trained prior they start from (mix5, mix10, droid, sim). The input pipeline padded the 18 real joints out to the model's 32 dims before normalising, so the 14 padding dims were normalised along with the real ones. Under quantile normalisation a degenerate padded dim maps to −1 rather than 0. Because pi05 uses discretestateinput, the state is binned into 256 levels and serialised as text, so those dims rendered as "0" (bin 0) instead of "128" (bin 128) — 14 of 32 state values differed and the state string grew by 28 tokens, diverging from any serving stack that pads after normalising. Padding now follows openpi's own order — Normalize first, then PadStatesAndActions — so the…

Geoffrey19/cei2-pi05-droid-real-112h-pickplace200 on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-30T08:12:28.926Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

Geoffrey19/cei2-pi05-droid-real-112h-pickplace200 is a robotics model repository published by Geoffrey19 on Hugging Face. The source reports the lerobot library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: robotics
Library: lerobot
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: 3,616,757,520
Architecture: Not reported
License: other
Access: Not gated by Hugging Face
Created: 2026-10-21T06:37:03.000Z
Last modified: 2026-10-21T06:41:19.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion