From d1548e1d1341564be7941396f6e71b7dc763825a Mon Sep 17 00:00:00 2001 From: Steven Palma Date: Sun, 26 Oct 2025 15:37:41 +0800 Subject: [PATCH] docs(install): imrpove groot and libero installation instructions (#2314) --- docs/source/groot.mdx | 5 ++++- docs/source/libero.mdx | 5 +++++ docs/source/pi0.mdx | 5 +++++ docs/source/pi05.mdx | 5 +++++ 4 files changed, 19 insertions(+), 1 deletion(-) diff --git a/docs/source/groot.mdx b/docs/source/groot.mdx index 02d70157..729a6465 100644 --- a/docs/source/groot.mdx +++ b/docs/source/groot.mdx @@ -40,7 +40,7 @@ python -c "import flash_attn; print(f'Flash Attention {flash_attn.__version__} i 3. Install LeRobot by running: ```bash -pip install lerobot[groot] # consider also installing libero,dev and test tags +pip install lerobot[groot] ``` ## Usage @@ -83,6 +83,9 @@ accelerate launch \ ### Libero Benchmark Results +> [!NOTE] +> Follow our instructions for Libero usage: [Libero](./libero) + GR00T has demonstrated strong performance on the Libero benchmark suite. To compare and test its LeRobot implementation, we finetuned the GR00T N1.5 model for 30k steps on the Libero dataset and compared the results to the GR00T reference results. | Benchmark | LeRobot Implementation | GR00T Reference | diff --git a/docs/source/libero.mdx b/docs/source/libero.mdx index 14f51ef3..f0448c3f 100644 --- a/docs/source/libero.mdx +++ b/docs/source/libero.mdx @@ -28,6 +28,11 @@ LIBERO is now part of our **multi-eval supported simulation**, meaning you can b To Install LIBERO, after following LeRobot official instructions, just do: `pip install -e ".[libero]"` +> [!NOTE] +> For lerobot 0.4.0, if you want to install libero tag, you will have to do: `pip install "lerobot[libero]@git+https://github.com/huggingface/lerobot.git"`. +> +> This will be solved in the next patch release + ### Single-suite evaluation Evaluate a policy on one LIBERO suite: diff --git a/docs/source/pi0.mdx b/docs/source/pi0.mdx index d36fe0ce..d15f7e91 100644 --- a/docs/source/pi0.mdx +++ b/docs/source/pi0.mdx @@ -28,6 +28,11 @@ As described by Physical Intelligence, while AI has achieved remarkable success pip install -e ".[pi]" ``` + > [!NOTE] + > For lerobot 0.4.0, if you want to install pi tag, you will have to do: `pip install "lerobot[pi]@git+https://github.com/huggingface/lerobot.git"`. + > + > This will be solved in the next patch release + ## Training Data and Capabilities π₀ is trained on the largest robot interaction dataset to date, combining three key data sources: diff --git a/docs/source/pi05.mdx b/docs/source/pi05.mdx index b6267fc5..29b79793 100644 --- a/docs/source/pi05.mdx +++ b/docs/source/pi05.mdx @@ -36,6 +36,11 @@ This diverse training mixture creates a "curriculum" that enables generalization pip install -e ".[pi]" ``` + > [!NOTE] + > For lerobot 0.4.0, if you want to install pi tag, you will have to do: `pip install "lerobot[pi]@git+https://github.com/huggingface/lerobot.git"`. + > + > This will be solved in the next patch release + ## Usage To use π₀.₅ in your LeRobot configuration, specify the policy type as: