Instructions to use Whalswp/groot_libero with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Whalswp/groot_libero with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Whalswp/groot_libero", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download H_Reader/Relation_Query/StateOnlyBalancedSO3/config.json from Whalswp/groot_libero: direct link, hf CLI and curl.
- Browser
- Download file 6.43 kB
-
https://huggingface.co/Whalswp/groot_libero/resolve/main/H_Reader/Relation_Query/StateOnlyBalancedSO3/config.json
- Command line
-
hf download hf://Whalswp/groot_libero/H_Reader/Relation_Query/StateOnlyBalancedSO3/config.json
-
curl -L -o config.json https://huggingface.co/Whalswp/groot_libero/resolve/main/H_Reader/Relation_Query/StateOnlyBalancedSO3/config.json
6.43 kB
| { | |
| "action_dim": 32, | |
| "action_head_cfg": { | |
| "action_dim": 32, | |
| "action_horizon": 16, | |
| "add_pos_embed": true, | |
| "backbone_embedding_dim": 2048, | |
| "diffusion_model_cfg": { | |
| "attention_head_dim": 48, | |
| "cross_attention_dim": 2048, | |
| "dropout": 0.2, | |
| "final_dropout": true, | |
| "interleave_self_attention": true, | |
| "norm_type": "ada_norm", | |
| "num_attention_heads": 32, | |
| "num_layers": 16, | |
| "output_dim": 1024, | |
| "positional_embeddings": null | |
| }, | |
| "hidden_size": 1024, | |
| "input_embedding_dim": 1536, | |
| "max_action_dim": 32, | |
| "max_state_dim": 64, | |
| "model_dtype": "float32", | |
| "noise_beta_alpha": 1.5, | |
| "noise_beta_beta": 1.0, | |
| "noise_s": 0.999, | |
| "num_inference_timesteps": 4, | |
| "num_target_vision_tokens": 32, | |
| "num_timestep_buckets": 1000, | |
| "tune_diffusion_model": true, | |
| "tune_projector": true, | |
| "use_vlln": true, | |
| "vl_self_attention_cfg": { | |
| "attention_head_dim": 64, | |
| "dropout": 0.2, | |
| "final_dropout": true, | |
| "num_attention_heads": 32, | |
| "num_layers": 4, | |
| "positional_embeddings": null | |
| } | |
| }, | |
| "action_horizon": 16, | |
| "architectures": [ | |
| "GR00T_N1_5" | |
| ], | |
| "attn_implementation": null, | |
| "backbone_cfg": { | |
| "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops", | |
| "load_bf16": false, | |
| "project_to_dim": null, | |
| "reproject_vision": false, | |
| "select_layer": 12, | |
| "tune_llm": false, | |
| "tune_visual": true, | |
| "use_flash_attention": true | |
| }, | |
| "clvla_auxiliary": { | |
| "action_loss_weight": 0.0, | |
| "action_teacher_enabled": false, | |
| "cross_attention_mode": "stock_h_context", | |
| "direct_q_supervision": true, | |
| "gradient_clip_max_norm": 1.0, | |
| "gradient_clipping": "joint_main_policy", | |
| "h_token_bottleneck": false, | |
| "isolated_query_initialization": true, | |
| "loss_weight": 1.0, | |
| "loss_weight_end": 1.0, | |
| "loss_weight_schedule": "constant", | |
| "policy_query_stop_gradient": false, | |
| "query_count": 1, | |
| "query_dim": 1536, | |
| "query_init_seed": 10042, | |
| "query_init_std": 0.02, | |
| "query_location": "after_future_before_action", | |
| "query_norm_mode": "stock_ada_norm", | |
| "relation_projector": false, | |
| "relation_tap_block": 7, | |
| "self_attention_mode": "stock_all_to_all", | |
| "source": "h_stock", | |
| "state_loss_weight": 1.0, | |
| "train_seed": 42 | |
| }, | |
| "clvla_inference_only_patch": false, | |
| "clvla_query_order": [ | |
| "state" | |
| ], | |
| "clvla_relation_mode": "state_only", | |
| "clvla_schema_version": "clvla_n15_internal_state_relation_query_v1", | |
| "clvla_state_teacher": { | |
| "combine": "weighted_rms_of_mean_normalized_component_distances", | |
| "component_normalization": { | |
| "checkpoint_embed_statistics_and_dataset_hashes": true, | |
| "degenerate_component_policy": "error", | |
| "fit_before_training": true, | |
| "fit_pair_count": 200000, | |
| "fit_pair_sampling": "uniform_unique_unordered_frame_pairs", | |
| "fit_pair_scope": "all_tasks_all_episodes", | |
| "fit_seed": 42, | |
| "fit_source": "training_dataset_only", | |
| "include_zero_component_distances": true, | |
| "method": "fixed_training_pair_mean", | |
| "minimum_mean_distance": 1e-08, | |
| "recompute_per_minibatch": false, | |
| "same_pairs_for_all_components": true, | |
| "statistics_path": "/home/work/workspace/test/seonho/groot_libero/teacher_stats/stateq_balanced_so3_all_pairs_seed42.json" | |
| }, | |
| "component_weights": { | |
| "gripper": 0.3333333333333333, | |
| "position": 0.3333333333333333, | |
| "rotation": 0.3333333333333333 | |
| }, | |
| "coordinate_statistics_path": "/home/work/workspace/test/seonho/libero/meta/stats.json", | |
| "coordinate_statistics_sha256": "1fe6c2d548a7998394488ae68bc2be46a51c8cd3798af6ab74fff79f8b20e293", | |
| "gripper_distance": "rms", | |
| "gripper_normalization": "train_minmax_minus1_plus1_no_clip", | |
| "gripper_slice": [ | |
| 6, | |
| 8 | |
| ], | |
| "mode": "balanced_so3", | |
| "position_distance": "rms", | |
| "position_normalization": "train_minmax_minus1_plus1_no_clip", | |
| "position_slice": [ | |
| 0, | |
| 3 | |
| ], | |
| "raw_column": "state", | |
| "resolved_component_means": [ | |
| 0.568242500099925, | |
| 0.7094815580930915, | |
| 0.7129484886172952 | |
| ], | |
| "resolved_component_statistics": { | |
| "component_means": [ | |
| 0.568242500099925, | |
| 0.7094815580930915, | |
| 0.7129484886172952 | |
| ], | |
| "component_order": [ | |
| "position", | |
| "rotation", | |
| "gripper" | |
| ], | |
| "dataset_hashes": { | |
| "episodes.jsonl": "0479a2ced6117700e4638a1da54dccd9f60ae5f47485ea6d91390c869befcf08", | |
| "info.json": "77c0da93c67960bac803a8ea25dabf380d752c26c1d91c54151121dd10e7d82f", | |
| "stats.json": "1fe6c2d548a7998394488ae68bc2be46a51c8cd3798af6ab74fff79f8b20e293", | |
| "tasks.jsonl": "e72ef3cf7ca7a3abe70b3e142a0d1acf2719d2a3f27598869092cc4f1762bb99" | |
| }, | |
| "fit_contract": { | |
| "fit_pair_count": 200000, | |
| "fit_pair_sampling": "uniform_unique_unordered_frame_pairs", | |
| "fit_pair_scope": "all_tasks_all_episodes", | |
| "fit_seed": 42, | |
| "include_zero_component_distances": true, | |
| "same_pairs_for_all_components": true | |
| }, | |
| "format": "libero_stateq_balanced_so3_v1", | |
| "frames": 273465, | |
| "pairs_sha256": "8b6ed0da15f4978101dce99e0f3406bd50cb7c6c94a01bbfae6a7b8f26042a6f", | |
| "raw_state_sha256": "93184ae0b189aa9dc3dee021060e24c5d86eebb07b72df0ce21ea9a9fee33efb" | |
| }, | |
| "resolved_coordinate_statistics": { | |
| "max": [ | |
| 0.21031762659549713, | |
| 0.39128610491752625, | |
| 1.3660105466842651, | |
| 3.6714255809783936, | |
| 3.560650587081909, | |
| 1.386339545249939, | |
| 0.04233968257904053, | |
| 0.0013633022317662835 | |
| ], | |
| "min": [ | |
| -0.4828203022480011, | |
| -0.3255046010017395, | |
| 0.008128180168569088, | |
| 0.35277295112609863, | |
| -3.641430377960205, | |
| -1.842738389968872, | |
| -0.0013586411951109767, | |
| -0.042040832340717316 | |
| ] | |
| }, | |
| "rotation_distance": "so3_geodesic_radians", | |
| "rotation_slice": [ | |
| 3, | |
| 6 | |
| ], | |
| "rotation_source_representation": "axis_angle", | |
| "source": "raw_libero_state_before_policy_transform" | |
| }, | |
| "clvla_variant": "internal_state_relation_query", | |
| "compute_dtype": "bfloat16", | |
| "hidden_size": 2048, | |
| "model_dtype": "float32", | |
| "model_type": "gr00t_n1_5", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.3" | |
| } | |