Other
Transformers
PyTorch
Safetensors
English
navfom
robotics
navigation
embodied-ai
waypoint-prediction
qwen
Instructions to use omlab/OmTrackVLA-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use omlab/OmTrackVLA-0.6B with Transformers:
# Load model directly from transformers import OpenTrackVLAForWaypoint model = OpenTrackVLAForWaypoint.from_pretrained("omlab/OmTrackVLA-0.6B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "source_checkpoint": "/data22/ying_heting/projects/opentrackvla/ckpt_0401_text/model_epoch01_step439700.pt", | |
| "converted_with": "convert_ckpt_to_hf.py", | |
| "config_overrides": { | |
| "train_json": [ | |
| "/data22/ying_heting/habitat_data/0330/stt_seed1000/", | |
| "/data22/ying_heting/habitat_data/0330/dt_seed1000/", | |
| "/data22/ying_heting/habitat_data/0330/at_seed1000/" | |
| ], | |
| "out_dir": "/data22/ying_heting/projects/opentrackvla/ckpt_0401_text", | |
| "n_waypoints": 8, | |
| "history": 31, | |
| "llm_name": "/data23/xu_ruochen/hf_models/Qwen3-0.6B-local", | |
| "epochs": 2, | |
| "batch_size": 8, | |
| "lr": 2e-05, | |
| "weight_decay": 0.01, | |
| "grad_clip": 1.0, | |
| "mixed_precision": true, | |
| "vision_feat_dim": 1536, | |
| "seed": 0, | |
| "num_workers": 4, | |
| "embodiment": "wheeled", | |
| "use_angle_tvi": false, | |
| "beta_nav": 10.0, | |
| "cache_root": [ | |
| "/data22/ying_heting/habitat_data/0330/stt_seed1000/vision_cache/", | |
| "/data22/ying_heting/habitat_data/0330/dt_seed1000/vision_cache/", | |
| "/data22/ying_heting/habitat_data/0330/at_seed1000/vision_cache/" | |
| ], | |
| "distributed": false, | |
| "dist_backend": "nccl", | |
| "use_indicator": false, | |
| "alpha_indicator": [ | |
| 1.0, | |
| 1.0 | |
| ], | |
| "alpha_wheeled": [ | |
| 1.0, | |
| 0.433, | |
| 2.09 | |
| ], | |
| "alpha_car": [ | |
| 50.8, | |
| 14.9, | |
| 1.52 | |
| ], | |
| "alpha_uav": [ | |
| 7.93, | |
| 3.19, | |
| 7.85, | |
| 1.04 | |
| ], | |
| "alpha_xy": 2.0, | |
| "log_every": 10, | |
| "csv_logging": false, | |
| "save_trajectories": false, | |
| "traj_subdir": "trajectories", | |
| "val_json": null, | |
| "eval_every": 0, | |
| "eval_batches": 8, | |
| "final_wp_threshold": 0.2, | |
| "episode_json": null, | |
| "episode_eval_every": 0, | |
| "episode_threshold": 0.2, | |
| "episode_max_frames": 256, | |
| "no_tanh_actions": true, | |
| "auto_indicator_scale": false, | |
| "max_ckpts": 3, | |
| "resume": true, | |
| "resume_ckpt": null, | |
| "infer_json": null, | |
| "infer_ckpt": null, | |
| "infer_out": "./infer_out", | |
| "infer_batches": 0, | |
| "infer_vis": false, | |
| "infer_save_npz": false | |
| }, | |
| "hf_config": { | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "torchscript": false, | |
| "dtype": "float32", | |
| "pruned_heads": {}, | |
| "tie_word_embeddings": true, | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "is_decoder": false, | |
| "cross_attention_hidden_size": null, | |
| "add_cross_attention": false, | |
| "tie_encoder_decoder": false, | |
| "architectures": [ | |
| "OpenTrackVLAForWaypoint" | |
| ], | |
| "finetuning_task": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "task_specific_params": null, | |
| "problem_type": null, | |
| "tokenizer_class": null, | |
| "prefix": null, | |
| "bos_token_id": null, | |
| "pad_token_id": null, | |
| "eos_token_id": null, | |
| "sep_token_id": null, | |
| "decoder_start_token_id": null, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "num_beams": 1, | |
| "temperature": 1.0, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "typical_p": 1.0, | |
| "repetition_penalty": 1.0, | |
| "length_penalty": 1.0, | |
| "no_repeat_ngram_size": 0, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "bad_words_ids": null, | |
| "num_return_sequences": 1, | |
| "output_scores": false, | |
| "return_dict_in_generate": false, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "remove_invalid_values": false, | |
| "exponential_decay_length_penalty": null, | |
| "suppress_tokens": null, | |
| "begin_suppress_tokens": null, | |
| "num_beam_groups": 1, | |
| "diversity_penalty": 0.0, | |
| "_name_or_path": "", | |
| "transformers_version": "4.57.3", | |
| "tf_legacy_loss": false, | |
| "use_bfloat16": false, | |
| "llm_name": "/data23/xu_ruochen/hf_models/Qwen3-0.6B-local", | |
| "freeze_llm": true, | |
| "n_waypoints": 8, | |
| "max_time": 4096, | |
| "beta_nav": 10.0, | |
| "use_angle_tvi": false, | |
| "use_tanh_actions": false, | |
| "alpha_xy": 2.0, | |
| "vision_feat_dim": 1536, | |
| "model_type": "navfom", | |
| "output_attentions": false | |
| }, | |
| "epoch": 1, | |
| "step": 439700 | |
| } |