Instructions to use TInkybala/Real_Panda_Merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use TInkybala/Real_Panda_Merged 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=TInkybala/Real_Panda_Merged \ --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=TInkybala/Real_Panda_Merged - Notebooks
- Google Colab
- Kaggle
| { | |
| "type": "smolvla", | |
| "n_obs_steps": 1, | |
| "input_features": { | |
| "observation.state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 8 | |
| ] | |
| }, | |
| "observation.images.camera_1": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 3, | |
| 480, | |
| 640 | |
| ] | |
| } | |
| }, | |
| "output_features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 7 | |
| ] | |
| } | |
| }, | |
| "device": "cuda", | |
| "use_amp": false, | |
| "use_peft": false, | |
| "push_to_hub": true, | |
| "repo_id": "TInkybala/Real_Panda_PickScrewdriver_finetune_smolvla_20260310_135104", | |
| "private": null, | |
| "tags": null, | |
| "license": null, | |
| "pretrained_path": null, | |
| "chunk_size": 50, | |
| "n_action_steps": 50, | |
| "normalization_mapping": { | |
| "VISUAL": "IDENTITY", | |
| "STATE": "MEAN_STD", | |
| "ACTION": "MEAN_STD" | |
| }, | |
| "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, | |
| "rtc_config": null, | |
| "compile_model": false, | |
| "compile_mode": "max-autotune" | |
| } |