v0.2.1: model.py finds instructions.json from the Hugging Face cache; link to the LeRobot version

README.md

@@ -93,7 +93,7 @@ so a clause or two may come out differently.
 With the benchmark (`pip install "amp-toy-robotics[packages]"`):
 
 ```bash
-hf download Adaptive-Machine-Patterns/amp-tadpole --revision v0.2.0 --local-dir amp-tadpole
+hf download Adaptive-Machine-Patterns/amp-tadpole --revision v0.2.1 --local-dir amp-tadpole
 amp-bench eval --policy amp-tadpole
 ```
 
@@ -112,6 +112,11 @@ model.eval()
 chunk = tadpole.predict(model, images, state, "Pick up the lime star")   # (8, 7)
 ```
 
+With [LeRobot](https://github.com/huggingface/lerobot): install
+[lerobot-policy-tadpole](https://github.com/Adaptive-Machine-Patterns/lerobot-policy-tadpole)
+and load [amp-tadpole-lerobot](https://huggingface.co/Adaptive-Machine-Patterns/amp-tadpole-lerobot),
+the same weights in LeRobot's format (`--policy.path=Adaptive-Machine-Patterns/amp-tadpole-lerobot`).
+
 With ONNX Runtime (any language, or the browser): `amp-tadpole.onnx` takes
 `images` uint8 (1, 3, 3, 512, 512), `tokens` int64 (1, 48), `token_mask`
 bool (1, 48) and `state` float32 (1, 7), and returns `chunk` (1, 8, 7).
@@ -171,10 +176,11 @@ teacher whose action is a fixed function of the state.
 
 | version | tag | what changed |
 |---|---|---|
+| 0.2.1 | `v0.2.1` | `model.py` now finds `instructions.json` when loaded from the Hugging Face cache; weights unchanged. AMP Tadpole for LeRobot: [amp-tadpole-lerobot](https://huggingface.co/Adaptive-Machine-Patterns/amp-tadpole-lerobot) |
 | 0.2.0 | `v0.2.0` | step 330,000, the end of the training run: 93.7% (from 88.2%), midpoint 75% (from 63%); checkpoint chosen on separate validation scenes |
 | 0.1.0 | `v0.1.0` | first preview: step 250,000. Its card said the 300 scenes were not used to choose the checkpoint; the training run's own checks used 100 of them (see Results) |
 
-Pin a version with `revision="v0.2.0"` (or `--revision v0.2.0`).
+Pin a version with `revision="v0.2.1"` (or `--revision v0.2.1`).
 
 ## Licence
 
@@ -207,7 +213,7 @@ a wrong movement could cause harm or damage.
   author    = {Whyte, Andy and {Adaptive Machine Patterns Ltd}},
   title     = {{AMP Tadpole}: a small vision-language-action model},
   year      = {2026},
-  version   = {0.2.0},
+  version   = {0.2.1},
   publisher = {Hugging Face},
   url       = {https://huggingface.co/Adaptive-Machine-Patterns/amp-tadpole}
 }

config.json

@@ -1,6 +1,6 @@
 {
   "model": "amp-tadpole",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "parameters": 6507335,
   "inputs": {
     "images": "uint8 (3, 3, 512, 512): top, side, iso",

model.py

@@ -28,7 +28,7 @@ import numpy as np
 import torch
 import torch.nn as nn
 
-HERE = Path(__file__).resolve().parent
+HERE = Path(__file__).absolute().parent      # not resolve(): in the Hugging Face cache the files are links to blobs
 GRID = 16             # tokens per camera side
 CHUNK = 8             # steps per answer
 STATE_DIM = 7

model.yaml

@@ -1,7 +1,7 @@
 # AMP Tadpole: a model package for the AMP Toy Robotics Benchmark
 # (and the AMP Embodied AI Workbench).  Format: the benchmark's README.
 name: AMP Tadpole
-version: 0.2.0
+version: 0.2.1
 author: Andy Whyte, Adaptive Machine Patterns Ltd
 license: CC-BY-NC-4.0 (commercial licences from Adaptive Machine Patterns Ltd)
 homepage: https://huggingface.co/Adaptive-Machine-Patterns/amp-tadpole