Instructions to use Orellius/so101_sort_smolvla with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use Orellius/so101_sort_smolvla 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=Orellius/so101_sort_smolvla \ --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=Orellius/so101_sort_smolvla - Notebooks
- Google Colab
- Kaggle
Upload policy weights, train config and readme
Browse files- README.md +1 -1
- config.json +2 -2
- model.safetensors +1 -1
- train_config.json +3 -3
README.md
CHANGED
|
@@ -6,8 +6,8 @@ license: apache-2.0
|
|
| 6 |
model_name: smolvla
|
| 7 |
pipeline_tag: robotics
|
| 8 |
tags:
|
| 9 |
-
- robotics
|
| 10 |
- smolvla
|
|
|
|
| 11 |
- lerobot
|
| 12 |
---
|
| 13 |
|
|
|
|
| 6 |
model_name: smolvla
|
| 7 |
pipeline_tag: robotics
|
| 8 |
tags:
|
|
|
|
| 9 |
- smolvla
|
| 10 |
+
- robotics
|
| 11 |
- lerobot
|
| 12 |
---
|
| 13 |
|
config.json
CHANGED
|
@@ -64,8 +64,8 @@
|
|
| 64 |
"optimizer_eps": 1e-08,
|
| 65 |
"optimizer_weight_decay": 1e-10,
|
| 66 |
"optimizer_grad_clip_norm": 10.0,
|
| 67 |
-
"scheduler_warmup_steps":
|
| 68 |
-
"scheduler_decay_steps":
|
| 69 |
"scheduler_decay_lr": 2.5e-06,
|
| 70 |
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
|
| 71 |
"load_vlm_weights": false,
|
|
|
|
| 64 |
"optimizer_eps": 1e-08,
|
| 65 |
"optimizer_weight_decay": 1e-10,
|
| 66 |
"optimizer_grad_clip_norm": 10.0,
|
| 67 |
+
"scheduler_warmup_steps": 350,
|
| 68 |
+
"scheduler_decay_steps": 7000,
|
| 69 |
"scheduler_decay_lr": 2.5e-06,
|
| 70 |
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
|
| 71 |
"load_vlm_weights": false,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1197789224
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6265a9d5b6b0b093f931192c8a92657d6aeabd8425f0081922d71b6fce508d72
|
| 3 |
size 1197789224
|
train_config.json
CHANGED
|
@@ -132,8 +132,8 @@
|
|
| 132 |
"optimizer_eps": 1e-08,
|
| 133 |
"optimizer_weight_decay": 1e-10,
|
| 134 |
"optimizer_grad_clip_norm": 10.0,
|
| 135 |
-
"scheduler_warmup_steps":
|
| 136 |
-
"scheduler_decay_steps":
|
| 137 |
"scheduler_decay_lr": 2.5e-06,
|
| 138 |
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
|
| 139 |
"load_vlm_weights": false,
|
|
@@ -154,7 +154,7 @@
|
|
| 154 |
"seed": 1000,
|
| 155 |
"num_workers": 4,
|
| 156 |
"batch_size": 4,
|
| 157 |
-
"steps":
|
| 158 |
"eval_freq": 200,
|
| 159 |
"log_freq": 100,
|
| 160 |
"save_checkpoint": true,
|
|
|
|
| 132 |
"optimizer_eps": 1e-08,
|
| 133 |
"optimizer_weight_decay": 1e-10,
|
| 134 |
"optimizer_grad_clip_norm": 10.0,
|
| 135 |
+
"scheduler_warmup_steps": 350,
|
| 136 |
+
"scheduler_decay_steps": 7000,
|
| 137 |
"scheduler_decay_lr": 2.5e-06,
|
| 138 |
"vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",
|
| 139 |
"load_vlm_weights": false,
|
|
|
|
| 154 |
"seed": 1000,
|
| 155 |
"num_workers": 4,
|
| 156 |
"batch_size": 4,
|
| 157 |
+
"steps": 7000,
|
| 158 |
"eval_freq": 200,
|
| 159 |
"log_freq": 100,
|
| 160 |
"save_checkpoint": true,
|