Upload simple MLP demo model with LeRobot model card

README.md

@@ -1,75 +1,66 @@
 ---
-library_name: pytorch
+datasets: demo/synthetic_data
+library_name: lerobot
 license: apache-2.0
 model_name: simple_mlp
+pipeline_tag: robotics
 tags:
+- demo
 - pytorch
-- neural-network
 - mlp
-- demo
+- robotics
+- neural-network
+- lerobot
+- simple_mlp
 ---
 
-# Simple Mlp
+# Model Card for simple_mlp
 
-This is a simple Multi-Layer Perceptron (MLP) neural network created for demonstration purposes.
+<!-- Provide a quick summary of what the model is/does. -->
 
-## Model Details
 
-- **Model Type**: simple_mlp
-- **Architecture**: feedforward
-- **Input Size**: 10
-- **Hidden Size**: 64
-- **Output Size**: 1
-- **Activation**: relu
+_Model type not recognized — please update this template._
 
-## Model Architecture
 
-```
-Sequential(
-  (0): Linear(in_features=10, out_features=64, bias=True)
-  (1): ReLU()
-  (2): Linear(in_features=64, out_features=64, bias=True)
-  (3): ReLU()
-  (4): Linear(in_features=64, out_features=1, bias=True)
-)
-```
+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).
 
-## Usage
+---
+
+## 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:
 
-```python
-import torch
-from huggingface_hub import hf_hub_download
-from safetensors.torch import load_model
+### Train from scratch
 
-# Download the model
-model_path = hf_hub_download(repo_id="your-repo-id", filename="model.safetensors")
+```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
+```
 
-# Create model instance
-model = SimpleMLP(
-    input_size=10, 
-    hidden_size=64, 
-    output_size=1
-)
+_Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
 
-# Load weights
-load_model(model, model_path)
-model.eval()
+### Evaluate the policy/run inference
 
-# Use the model
-x = torch.randn(1, 10)
-output = model(x)
+```bash
+lerobot-record \
+  --robot.type=so100_follower \
+  --dataset.repo_id=<hf_user>/eval_<dataset> \
+  --policy.path=<hf_user>/<desired_policy_repo_id> \
+  --episodes=10
 ```
 
-## Training
+Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
 
-This model was trained on randomly generated data for demonstration purposes:
-- Training samples: 100
-- Epochs: 50
-- Optimizer: Adam
-- Learning rate: 0.001
-- Loss function: MSE Loss
+---
 
-## Files
+## Model Details
 
-- `model.safetensors`: Model weights in SafeTensors format
-- `config.json`: Model configuration
+- **License:** apache-2.0

config.json

@@ -1,8 +1,13 @@
 {
   "model_type": "simple_mlp",
+  "architecture": "mlp",
   "input_size": 10,
   "hidden_size": 64,
   "output_size": 1,
-  "architecture": "feedforward",
-  "activation": "relu"
+  "activation": "relu",
+  "epochs": 50,
+  "learning_rate": 0.001,
+  "optimizer": "adam",
+  "loss_function": "mse",
+  "dataset_size": 100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00b7544c6c3b39938f666f731aa976d0b49ef1c6a5aa53f4124b726239d6586e
+oid sha256:7ac5536f7d0a519640464c7e2df15c86138b12b12859d132616f5918625678d2
 size 20172