Upload policy weights, train config and readme

README.md

@@ -0,0 +1,63 @@
+---
+base_model: lerobot/smolvla_base
+datasets: sleepyguy25/so1000
+library_name: lerobot
+license: apache-2.0
+model_name: smolvla
+pipeline_tag: robotics
+tags:
+- robotics
+- smolvla
+- lerobot
+---
+
+# Model Card for smolvla
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+[SmolVLA](https://huggingface.co/papers/2506.01844) is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware.
+
+
+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

@@ -41,7 +41,7 @@
     "device": "cuda",
     "use_amp": false,
     "push_to_hub": true,
-    "repo_id": "sleepyguy25smol",
+    "repo_id": "sleepyguy25/smol",
     "private": null,
     "tags": null,
     "license": null,
@@ -69,7 +69,7 @@
     ],
     "optimizer_eps": 1e-08,
     "optimizer_weight_decay": 1e-10,
-    "optimizer_grad_clip_norm": 10,
+    "optimizer_grad_clip_norm": 10.0,
     "scheduler_warmup_steps": 1000,
     "scheduler_decay_steps": 30000,
     "scheduler_decay_lr": 2.5e-06,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82f0deb01cba2c939da11f5b3bc3d1590bb244917b17468587f584a132a6034b
+oid sha256:cedf9be28ea7cb4e0d3df9f5abd8e25b80ebdef717465bd48bc95bbfef52313c
 size 906498200

train_config.json

@@ -1,6 +1,6 @@
 {
     "dataset": {
-        "repo_id": "sleepyguy25/pick",
+        "repo_id": "sleepyguy25/so1000",
         "root": "data",
         "episodes": null,
         "image_transforms": {
@@ -108,7 +108,7 @@
         "device": "cuda",
         "use_amp": false,
         "push_to_hub": true,
-        "repo_id": "sleepyguy25smol",
+        "repo_id": "sleepyguy25/smol",
         "private": null,
         "tags": null,
         "license": null,
@@ -136,7 +136,7 @@
         ],
         "optimizer_eps": 1e-08,
         "optimizer_weight_decay": 1e-10,
-        "optimizer_grad_clip_norm": 10,
+        "optimizer_grad_clip_norm": 10.0,
         "scheduler_warmup_steps": 1000,
         "scheduler_decay_steps": 30000,
         "scheduler_decay_lr": 2.5e-06,
@@ -153,13 +153,13 @@
         "min_period": 0.004,
         "max_period": 4.0
     },
-    "output_dir": "outputs/train/my_smolvla",
+    "output_dir": "outputs/train/my_smolvla1",
     "job_name": "my_smolvla_training",
     "resume": false,
     "seed": 1000,
     "num_workers": 4,
     "batch_size": 16,
-    "steps": 3700,
+    "steps": 5000,
     "eval_freq": 500,
     "log_freq": 100,
     "save_checkpoint": true,
@@ -169,7 +169,7 @@
         "type": "adamw",
         "lr": 0.0001,
         "weight_decay": 1e-10,
-        "grad_clip_norm": 10,
+        "grad_clip_norm": 10.0,
         "betas": [
             0.9,
             0.95