Upload policy

README.md

@@ -0,0 +1,64 @@
+---
+base_model: lerobot/smolvla_base
+datasets:
+- imstevenpmwork/thanos_picking_power_gem_1749731584242992
+library_name: lerobot
+license: apache-2.0
+model_name: smolvla
+pipeline_tag: robotics
+tags:
+- robotics
+- smolvla
+model_summary: '[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.'
+---
+
+# 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:
+
+### 1 Train from scratch
+
+```bash
+python lerobot/scripts/train.py \
+  --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/`.*
+
+### 2 Evaluate the policy
+
+```bash
+python -m 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 +1,94 @@
+{
+    "type": "smolvla",
+    "n_obs_steps": 1,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "MEAN_STD",
+        "ACTION": "MEAN_STD"
+    },
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        },
+        "observation.images.front": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.images.eagle": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.images.glove": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "device": "mps",
+    "use_amp": false,
+    "push_to_hub": true,
+    "repo_id": "pepijn223/my_policy22",
+    "dataset_repo_id": "imstevenpmwork/thanos_picking_power_gem_1749731584242992",
+    "chunk_size": 50,
+    "n_action_steps": 50,
+    "max_state_dim": 32,
+    "max_action_dim": 32,
+    "resize_imgs_with_padding": [
+        512,
+        512
+    ],
+    "empty_cameras": 0,
+    "adapt_to_pi_aloha": false,
+    "use_delta_joint_actions_aloha": false,
+    "tokenizer_max_length": 48,
+    "num_steps": 10,
+    "use_cache": true,
+    "freeze_vision_encoder": true,
+    "train_expert_only": true,
+    "train_state_proj": true,
+    "optimizer_lr": 0.0001,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 1e-10,
+    "optimizer_grad_clip_norm": 10,
+    "scheduler_warmup_steps": 1000,
+    "scheduler_decay_steps": 30000,
+    "scheduler_decay_lr": 2.5e-06,
+    "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
+    "load_vlm_weights": false,
+    "add_image_special_tokens": false,
+    "attention_mode": "cross_attn",
+    "prefix_length": -1,
+    "pad_language_to": "longest",
+    "num_expert_layers": -1,
+    "num_vlm_layers": 16,
+    "self_attn_every_n_layers": 2,
+    "expert_width_multiplier": 0.75,
+    "min_period": 0.004,
+    "max_period": 4.0
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67410f443d0747f4f3360792aa2eff6931f8b946cb0b7cbb2a8035cac3de1308
+size 1197790016