Upload PI0.5 PyTorch base model

README.md

@@ -0,0 +1,70 @@
+---
+datasets: unknown
+library_name: lerobot
+license: apache-2.0
+model_name: pi05
+pipeline_tag: robotics
+tags:
+- pi05
+- robotics
+- lerobot
+---
+
+# Model Card for pi05
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+**π₀.₅ (Pi05) Policy**
+
+π₀.₅ is a Vision-Language-Action model with open-world generalization, from Physical Intelligence. The LeRobot implementation is adapted from their open source OpenPI repository.
+
+**Model Overview**
+
+π₀.₅ represents a significant evolution from π₀, developed by Physical Intelligence to address a big challenge in robotics: open-world generalization. While robots can perform impressive tasks in controlled environments, π₀.₅ is designed to generalize to entirely new environments and situations that were never seen during training.
+
+For more details, see the [Physical Intelligence π₀.₅ blog post](https://www.physicalintelligence.company/blog/pi05).
+
+
+This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
+See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
+
+---
+
+## How to Get Started with the Model
+
+For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
+Below is the short version on how to train and run inference/eval:
+
+### Train from scratch
+
+```bash
+lerobot-train \
+  --dataset.repo_id=${HF_USER}/<dataset> \
+  --policy.type=act \
+  --output_dir=outputs/train/<desired_policy_repo_id> \
+  --job_name=lerobot_training \
+  --policy.device=cuda \
+  --policy.repo_id=${HF_USER}/<desired_policy_repo_id>
+  --wandb.enable=true
+```
+
+_Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
+
+### Evaluate the policy/run inference
+
+```bash
+lerobot-record \
+  --robot.type=so100_follower \
+  --dataset.repo_id=<hf_user>/eval_<dataset> \
+  --policy.path=<hf_user>/<desired_policy_repo_id> \
+  --episodes=10
+```
+
+Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
+
+---
+
+## Model Details
+
+- **License:** apache-2.0

config.json

@@ -0,0 +1,92 @@
+{
+    "type": "pi05",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                14
+            ]
+        },
+        "observation.images.top": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        },
+        "observation.images.left": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        },
+        "observation.images.right": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                14
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "push_to_hub": true,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "paligemma_variant": "gemma_2b",
+    "action_expert_variant": "gemma_300m",
+    "dtype": "bfloat16",
+    "chunk_size": 50,
+    "n_action_steps": 50,
+    "max_state_dim": 32,
+    "max_action_dim": 32,
+    "num_inference_steps": 10,
+    "time_sampling_beta_alpha": 1.5,
+    "time_sampling_beta_beta": 1.0,
+    "time_sampling_scale": 0.999,
+    "time_sampling_offset": 0.001,
+    "min_period": 0.004,
+    "max_period": 4.0,
+    "rtc_config": null,
+    "image_resolution": [
+        224,
+        224
+    ],
+    "empty_cameras": 0,
+    "tokenizer_max_length": 200,
+    "normalization_mapping": {
+        "VISUAL": "MEAN_STD",
+        "STATE": "MIN_MAX",
+        "ACTION": "MEAN_STD"
+    },
+    "gradient_checkpointing": true,
+    "compile_model": false,
+    "compile_mode": "max-autotune",
+    "optimizer_lr": 2.5e-05,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 0.01,
+    "optimizer_grad_clip_norm": 1.0,
+    "scheduler_warmup_steps": 1000,
+    "scheduler_decay_steps": 30000,
+    "scheduler_decay_lr": 2.5e-06
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f793f192f77b896de5ea6454e7b5fe471c07bed8d4f8e6b976ff8c386ad4bd6d
+size 14467170760

policy_postprocessor.json

@@ -0,0 +1,48 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    },
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ],
+            "normalization": {
+              "mode": "MEAN_STD",
+              "mean": [
+                -9.538637424210057,
+                -23.303302123398584,
+                27.980357810668227,
+                71.35812899968884,
+                4.055796461816514,
+                12.675294114861119
+              ],
+              "std": [
+                19.682557487896783,
+                34.25780489772143,
+                32.804336590385184,
+                13.80158144415263,
+                9.76913612979956,
+                8.606452004202943
+              ]
+            }
+          }
+        },
+        "norm_map": {
+          "ACTION": "MEAN_STD"
+        }
+      }
+    }
+  ]
+}

policy_preprocessor.json

@@ -0,0 +1,142 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {}
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "observation.state": {
+            "type": "STATE",
+            "shape": [
+              6
+            ],
+            "normalization": {
+              "mode": "MIN_MAX",
+              "min": [
+                -54.06871795654297,
+                -97.31949615478516,
+                -29.040971755981445,
+                35.838382720947266,
+                -19.853479385375977,
+                0.737265408039093
+              ],
+              "max": [
+                34.32188034057617,
+                35.40856170654297,
+                99.1895523071289,
+                98.30303192138672,
+                29.377288818359375,
+                30.697050094604492
+              ]
+            }
+          },
+          "observation.images.top": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              224,
+              224
+            ],
+            "normalization": {
+              "mode": "MEAN_STD",
+              "mean": [
+                0.4534227455943007,
+                0.42901222558577234,
+                0.4044911766773638
+              ],
+              "std": [
+                0.2815573315091434,
+                0.2542026950261449,
+                0.2563229871857081
+              ]
+            }
+          },
+          "observation.images.wrist": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              224,
+              224
+            ],
+            "normalization": {
+              "mode": "MEAN_STD",
+              "mean": [
+                0.5329215492594676,
+                0.49891376312335955,
+                0.5109464269401987
+              ],
+              "std": [
+                0.31091577456313274,
+                0.29490511281918097,
+                0.31577234793989206
+              ]
+            }
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ],
+            "normalization": {
+              "mode": "MEAN_STD",
+              "mean": [
+                -9.538637424210057,
+                -23.303302123398584,
+                27.980357810668227,
+                71.35812899968884,
+                4.055796461816514,
+                12.675294114861119
+              ],
+              "std": [
+                19.682557487896783,
+                34.25780489772143,
+                32.804336590385184,
+                13.80158144415263,
+                9.76913612979956,
+                8.606452004202943
+              ]
+            }
+          }
+        },
+        "norm_map": {
+          "VISUAL": "MEAN_STD",
+          "STATE": "MIN_MAX",
+          "ACTION": "MEAN_STD"
+        }
+      }
+    },
+    {
+      "registry_name": "pi05_prepare_state_tokenizer_processor_step",
+      "config": {}
+    },
+    {
+      "registry_name": "tokenizer_processor",
+      "config": {
+        "max_length": 200,
+        "task_key": "task",
+        "padding_side": "right",
+        "padding": "max_length",
+        "truncation": true,
+        "tokenizer_name": "google/paligemma-3b-pt-224"
+      }
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    }
+  ]
+}