Robotics
LeRobot
Safetensors
smolvla
pytorch_model_hub_mixin
IB-Robot
LeRobot
vision-language-action
rknn
edge-deployment
Instructions to use openEuler/smolvla with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use openEuler/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=openEuler/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=openEuler/smolvla - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "SmolVLMForConditionalGeneration" | |
| ], | |
| "image_token_id": 49190, | |
| "model_type": "smolvlm", | |
| "pad_token_id": 128002, | |
| "scale_factor": 4, | |
| "text_config": { | |
| "_flash_attn_2_enabled": true, | |
| "_name_or_path": "None", | |
| "architectures": [ | |
| "VLlama3ForCausalLM" | |
| ], | |
| "head_dim": 64, | |
| "hidden_size": 960, | |
| "intermediate_size": 2560, | |
| "is_llama_config": true, | |
| "max_position_embeddings": 8192, | |
| "model_type": "llama", | |
| "neftune_noise_alpha": 0.0, | |
| "num_attention_heads": 15, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 5, | |
| "pad_token_id": 2, | |
| "perceiver_config": { | |
| "_attn_implementation_autoset": false, | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "silu", | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "vllama3", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_key_value_heads": 1, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "qk_layer_norms_perceiver": false, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "resampler_depth": 6, | |
| "resampler_head_dim": 96, | |
| "resampler_n_heads": 16, | |
| "resampler_n_latents": 64, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "transformers_version": "4.46.0", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| }, | |
| "pixel_shuffle_factor": 4, | |
| "qk_layer_norms": false, | |
| "rms_norm_eps": 1e-05, | |
| "rope_interleaved": false, | |
| "rope_theta": 100000, | |
| "torch_dtype": "bfloat16", | |
| "transformers.js_config": { | |
| "kv_cache_dtype": { | |
| "fp16": "float16", | |
| "q4f16": "float16" | |
| } | |
| }, | |
| "use_resampler": false, | |
| "vocab_size": 49280 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers.js_config": { | |
| "kv_cache_dtype": { | |
| "fp16": "float16", | |
| "q4f16": "float16" | |
| } | |
| }, | |
| "transformers_version": "4.47.1", | |
| "use_cache": false, | |
| "use_reentrant_checkpointing": false, | |
| "vision_config": { | |
| "hidden_size": 768, | |
| "image_size": 512, | |
| "max_image_size": { | |
| "longest_edge": 512 | |
| }, | |
| "model_type": "smolvlm_vision", | |
| "num_attention_heads": 12, | |
| "patch_size": 16, | |
| "size": { | |
| "longest_edge": 2048 | |
| }, | |
| "tie_word_embeddings": false, | |
| "use_base_siglip": false | |
| }, | |
| "vocab_size": 49280 | |
| } | |