| { |
| "id": "qwen3_omni_lora", |
| "display_name": "Qwen3-Omni LoRA", |
| "status": "implemented", |
| "model_family": "Qwen3-Omni", |
| "default_model_id": "Qwen/Qwen3-Omni-30B-A3B-Instruct", |
| "local_model_env": "MODEL_DIR", |
| "dataset_contract": "xperience10m_episode_json_qa_v1", |
| "training_objective": "structured_episode_understanding_json_qa", |
| "split_policy": { |
| "unit": "episode", |
| "default_counts": { |
| "train": 96, |
| "val": 16, |
| "test": 16 |
| }, |
| "leakage_guard": "episode_id and path-qualified session split checks" |
| }, |
| "modalities": { |
| "direct_inputs": [ |
| "multi-camera rendered mosaic video", |
| "AAC audio extracted from fisheye_cam0 MP4", |
| "language prompt and label options" |
| ], |
| "bridged_inputs": [ |
| "depth and confidence", |
| "pose and SLAM trajectory", |
| "body and hand mocap", |
| "IMU acceleration and gyro", |
| "object/contact summary features" |
| ], |
| "excluded_inputs": [ |
| "visualization.rrd" |
| ] |
| }, |
| "entrypoints": { |
| "selection_manifest": "scripts/omni/build_selection_episode_manifest.py", |
| "export": "scripts/omni/parallel_export_qwen3_omni_action_dataset.py", |
| "neutral_index": "scripts/omni/export_model_neutral_window_index.py", |
| "train": "scripts/omni/train_qwen3_omni_lora.py", |
| "eval": "scripts/omni/eval_qwen3_omni_lora.py", |
| "watch": "scripts/omni/watch_omni_train_then_eval.py", |
| "launcher": "scripts/omni/run_128_fullsplit_parallel_export_8gpu.sh", |
| "upload": "scripts/omni/upload_qwen3_omni_lora_to_hf.py", |
| "validate": "scripts/omni/validate_omni_finetune_run.py" |
| }, |
| "primary_metrics": [ |
| "json_validity_rate", |
| "action_macro_f1", |
| "subtask_accuracy", |
| "transition_accuracy", |
| "next_action_accuracy", |
| "contact_accuracy", |
| "object_micro_f1", |
| "held_out_episode_count" |
| ], |
| "artifact_contract": { |
| "checkpoint_gate": "lora_safetensors_shape_check", |
| "required_eval_files": [ |
| "metrics.json", |
| "predictions.jsonl", |
| "predictions.csv", |
| "per_class_metrics.csv", |
| "confusion_matrix.csv", |
| "RUN_REPORT.md" |
| ], |
| "required_training_files": [ |
| "training_metadata.json", |
| "progress.jsonl", |
| "adapter_config.json", |
| "adapter_model.safetensors" |
| ], |
| "public_package_allowed": [ |
| "metrics", |
| "predictions", |
| "confusion matrices", |
| "run reports", |
| "episode and dataset manifests", |
| "training metadata", |
| "validation summaries" |
| ], |
| "public_package_forbidden": [ |
| "raw MP4", |
| "annotation HDF5", |
| "Rerun RRD", |
| "base-model weights", |
| "LoRA adapter weights", |
| "full checkpoints", |
| "large archives" |
| ] |
| }, |
| "extension_requirements": [] |
| } |
|
|
