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/StateRawActionRaw/config.json from Whalswp/groot_libero: direct link, hf CLI and curl.
- Browser
- Download file 2.87 kB
-
https://huggingface.co/Whalswp/groot_libero/resolve/main/H_Reader/Relation_Query/StateRawActionRaw/config.json
- Command line
-
hf download hf://Whalswp/groot_libero/H_Reader/Relation_Query/StateRawActionRaw/config.json
-
curl -L -o config.json https://huggingface.co/Whalswp/groot_libero/resolve/main/H_Reader/Relation_Query/StateRawActionRaw/config.json
2.87 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": 1.0, | |
| "action_teacher_enabled": true, | |
| "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": 2, | |
| "query_dim": 1536, | |
| "query_init_seeds": { | |
| "action": 10043, | |
| "state": 10042 | |
| }, | |
| "query_init_std": 0.02, | |
| "query_location": "after_future_before_action", | |
| "query_norm_mode": "stock_ada_norm", | |
| "query_order": [ | |
| "state", | |
| "action" | |
| ], | |
| "relation_projector": false, | |
| "relation_tap_block": 7, | |
| "self_attention_mode": "stock_all_to_all", | |
| "source": "dit_internal_relation_queries", | |
| "state_loss_weight": 1.0, | |
| "train_seed": 42 | |
| }, | |
| "clvla_query_order": [ | |
| "state", | |
| "action" | |
| ], | |
| "clvla_schema_version": "clvla_n15_internal_state_action_relation_query_v1", | |
| "clvla_variant": "internal_state_action_relation_query", | |
| "compute_dtype": "bfloat16", | |
| "hidden_size": 2048, | |
| "model_dtype": "float32", | |
| "model_type": "gr00t_n1_5", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.3" | |
| } | |