Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,43 @@
+---
+library_name: openpi
+tags:
+- robotics
+- openpi
+- pi0
+- franka
+---
+
+# EXP3_20_a100
+
+openpi π₀.₅ policy checkpoint.
+
+- **Train config:** `pi05_Franka_EXP3_20`
+- **Experiment:** `EXP3_20_a100`
+- **Checkpoints in this repo:**
+
+- `step_5999/`
+
+Each folder is one training step and is self-contained.
+- **Training dataset:** [saifahmad123/EXP3_50](https://huggingface.co/datasets/saifahmad123/EXP3_50)
+
+## Contents
+
+| Path | Purpose |
+|---|---|
+| `step_5999/params/` | Model weights. Required to serve the policy. |
+| `step_5999/assets/` | Normalization statistics. Required to serve the policy. |
+| `step_5999/train_state/` | Optimizer state. Only present if uploaded with `--include-train-state`; needed to resume training. |
+
+## Usage
+
+```python
+from huggingface_hub import snapshot_download
+from openpi.policies import policy_config
+from openpi.training import config as _config
+
+ckpt = snapshot_download("saifahmad123/EXP3_20_a100", allow_patterns="step_5999/*") + "/step_5999"
+train_config = _config.get_config("pi05_Franka_EXP3_20")
+policy = policy_config.create_trained_policy(train_config, ckpt)
+
+action_chunk = policy.infer(observation)["actions"]
+```