Instructions to use mimimimi2002/smolvla_object_force_new with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use mimimimi2002/smolvla_object_force_new with LeRobot:
# See https://github.com/huggingface/lerobot?tab=readme-ov-file#installation for more details git clone https://github.com/huggingface/lerobot.git cd lerobot pip install -e .[smolvla]
# Launch finetuning on your dataset python lerobot/scripts/train.py \ --policy.path=mimimimi2002/smolvla_object_force_new \ --dataset.repo_id=lerobot/svla_so101_pickplace \ --batch_size=64 \ --steps=20000 \ --output_dir=outputs/train/my_smolvla \ --job_name=my_smolvla_training \ --policy.device=cuda \ --wandb.enable=true
# Run the policy using the record function python -m lerobot.record \ --robot.type=so101_follower \ --robot.port=/dev/ttyACM0 \ # <- Use your port --robot.id=my_blue_follower_arm \ # <- Use your robot id --robot.cameras="{ front: {type: opencv, index_or_path: 8, width: 640, height: 480, fps: 30}}" \ # <- Use your cameras --dataset.single_task="Grasp a lego block and put it in the bin." \ # <- Use the same task description you used in your dataset recording --dataset.repo_id=HF_USER/dataset_name \ # <- This will be the dataset name on HF Hub --dataset.episode_time_s=50 \ --dataset.num_episodes=10 \ --policy.path=mimimimi2002/smolvla_object_force_new - Notebooks
- Google Colab
- Kaggle
Upload policy weights, train config and readme
Browse files- README.md +63 -0
- config.json +2 -2
- model.safetensors +2 -2
- train_config.json +3 -3
README.md
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: lerobot/smolvla_base
|
| 3 |
+
datasets: mimimimi2002/object_force_fixed
|
| 4 |
+
library_name: lerobot
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
model_name: smolvla
|
| 7 |
+
pipeline_tag: robotics
|
| 8 |
+
tags:
|
| 9 |
+
- lerobot
|
| 10 |
+
- robotics
|
| 11 |
+
- smolvla
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Model Card for smolvla
|
| 15 |
+
|
| 16 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
[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.
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
|
| 23 |
+
See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
|
| 24 |
+
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
## How to Get Started with the Model
|
| 28 |
+
|
| 29 |
+
For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
|
| 30 |
+
Below is the short version on how to train and run inference/eval:
|
| 31 |
+
|
| 32 |
+
### Train from scratch
|
| 33 |
+
|
| 34 |
+
```bash
|
| 35 |
+
python -m lerobot.scripts.train \
|
| 36 |
+
--dataset.repo_id=${HF_USER}/<dataset> \
|
| 37 |
+
--policy.type=act \
|
| 38 |
+
--output_dir=outputs/train/<desired_policy_repo_id> \
|
| 39 |
+
--job_name=lerobot_training \
|
| 40 |
+
--policy.device=cuda \
|
| 41 |
+
--policy.repo_id=${HF_USER}/<desired_policy_repo_id>
|
| 42 |
+
--wandb.enable=true
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
+
_Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
|
| 46 |
+
|
| 47 |
+
### Evaluate the policy/run inference
|
| 48 |
+
|
| 49 |
+
```bash
|
| 50 |
+
python -m lerobot.record \
|
| 51 |
+
--robot.type=so100_follower \
|
| 52 |
+
--dataset.repo_id=<hf_user>/eval_<dataset> \
|
| 53 |
+
--policy.path=<hf_user>/<desired_policy_repo_id> \
|
| 54 |
+
--episodes=10
|
| 55 |
+
```
|
| 56 |
+
|
| 57 |
+
Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
|
| 58 |
+
|
| 59 |
+
---
|
| 60 |
+
|
| 61 |
+
## Model Details
|
| 62 |
+
|
| 63 |
+
- **License:** apache-2.0
|
config.json
CHANGED
|
@@ -43,7 +43,7 @@
|
|
| 43 |
"n_action_steps": 50,
|
| 44 |
"max_state_dim": 32,
|
| 45 |
"max_action_dim": 32,
|
| 46 |
-
"max_force_dim":
|
| 47 |
"resize_imgs_with_padding": [
|
| 48 |
512,
|
| 49 |
512
|
|
@@ -80,4 +80,4 @@
|
|
| 80 |
"expert_width_multiplier": 0.75,
|
| 81 |
"min_period": 0.004,
|
| 82 |
"max_period": 4.0
|
| 83 |
-
}
|
|
|
|
| 43 |
"n_action_steps": 50,
|
| 44 |
"max_state_dim": 32,
|
| 45 |
"max_action_dim": 32,
|
| 46 |
+
"max_force_dim": 12,
|
| 47 |
"resize_imgs_with_padding": [
|
| 48 |
512,
|
| 49 |
512
|
|
|
|
| 80 |
"expert_width_multiplier": 0.75,
|
| 81 |
"min_period": 0.004,
|
| 82 |
"max_period": 4.0
|
| 83 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55fae1b61837d5b856864ec094d8c82ca26c574cfc461634e4434dfff12d868d
|
| 3 |
+
size 906763136
|
train_config.json
CHANGED
|
@@ -110,7 +110,7 @@
|
|
| 110 |
"n_action_steps": 50,
|
| 111 |
"max_state_dim": 32,
|
| 112 |
"max_action_dim": 32,
|
| 113 |
-
"max_force_dim":
|
| 114 |
"resize_imgs_with_padding": [
|
| 115 |
512,
|
| 116 |
512
|
|
@@ -148,7 +148,7 @@
|
|
| 148 |
"min_period": 0.004,
|
| 149 |
"max_period": 4.0
|
| 150 |
},
|
| 151 |
-
"output_dir": "outputs/train/2026-01-
|
| 152 |
"job_name": "smolvla",
|
| 153 |
"resume": false,
|
| 154 |
"seed": 1000,
|
|
@@ -189,7 +189,7 @@
|
|
| 189 |
"project": "smolvla_force_finetune",
|
| 190 |
"entity": null,
|
| 191 |
"notes": "tactile force smolvla train with force",
|
| 192 |
-
"run_id": "
|
| 193 |
"mode": "online"
|
| 194 |
}
|
| 195 |
}
|
|
|
|
| 110 |
"n_action_steps": 50,
|
| 111 |
"max_state_dim": 32,
|
| 112 |
"max_action_dim": 32,
|
| 113 |
+
"max_force_dim": 12,
|
| 114 |
"resize_imgs_with_padding": [
|
| 115 |
512,
|
| 116 |
512
|
|
|
|
| 148 |
"min_period": 0.004,
|
| 149 |
"max_period": 4.0
|
| 150 |
},
|
| 151 |
+
"output_dir": "outputs/train/2026-01-23/11-22-58_smolvla",
|
| 152 |
"job_name": "smolvla",
|
| 153 |
"resume": false,
|
| 154 |
"seed": 1000,
|
|
|
|
| 189 |
"project": "smolvla_force_finetune",
|
| 190 |
"entity": null,
|
| 191 |
"notes": "tactile force smolvla train with force",
|
| 192 |
+
"run_id": "4t4bolc0",
|
| 193 |
"mode": "online"
|
| 194 |
}
|
| 195 |
}
|