AI & LLM Engineering · VectorSpaceLab/AREX-Skill

Use Torch Points3D for point-cloud deep learning APIs, datasets/transforms, Hydra training/evaluation, checkpoints, sparse backend decisions, and registration workflows.

VectorSpaceLab/AREX-Skill

A skill your agent uses for Torch-TensorRT tasks: compiling PyTorch models with TensorRT, dynamic-shape/export workflows, runtime optimization, Triton/C++/distributed deployment, debugging…

VectorSpaceLab/AREX-Skill

Use TorchMetrics to choose, inspect, and combine metric families for PyTorch evaluation, including core API, domain metrics, model-based metrics, and wrappers.

VectorSpaceLab/AREX-Skill

Use TorchRL for TensorDict-first reinforcement-learning environments, collectors, replay buffers, modules, objectives, LLM/RLHF/VLA workflows, services, rendering, and maintainer-safe repository…

VectorSpaceLab/AREX-Skill

A skill your agent uses when working with TorchVision models, weights, transforms, TVTensors, datasets, image IO, visualization utilities, vision ops, detection helpers, or official reference…

VectorSpaceLab/AREX-Skill

A skill your agent uses for Ultralytics track mode, tracker YAML selection, persistent object IDs, and YOLO Solutions such as counting, heatmaps, speed, queue, region, similarity search, and…

VectorSpaceLab/AREX-Skill

Train or fine-tune ColBERT models, prepare and validate triples, use scored distillation examples, and plan GPU/resource settings.

VectorSpaceLab/AREX-Skill

A skill your agent uses for ModelScope trainer construction, TrainingArgs conversion, fine-tuning and evaluation preflight, checkpoint hooks, and safe train/eval command planning.

VectorSpaceLab/AREX-Skill

Use Towhee's optional PyTorch Trainer, TrainingConfig YAML, NNOperator training bridge, and towhee.models package boundaries safely.

VectorSpaceLab/AREX-Skill

A skill your agent uses when planning or auditing TorchVision reference training/evaluation workflows for classification, quantization, detection, segmentation, video classification, optical flow…

VectorSpaceLab/AREX-Skill

Compose timm API-level training loops with optimizer and scheduler factories, loss selection, task wrappers, EMA, AMP scaling, metrics, checkpoint state, and safe CPU smoke checks.

VectorSpaceLab/AREX-Skill

A skill your agent uses for Ultralytics YOLO package workflows: CLI/Python model usage, data/config setup, train/val, prediction/results, export/deployment, tracking/solutions, model-family…

VectorSpaceLab/AREX-Skill

Use this sub-skill for MLAlgorithms clustering, Gaussian mixtures, PCA, t-SNE, RBM feature learning, metrics/distances, and packaged demo dataset loaders.

VectorSpaceLab/AREX-Skill

Guide safe video-file, webcam, and optional half-precision demo use for pytorch-yolo-v3.

VectorSpaceLab/AREX-Skill

A skill your agent uses for clone-run Ultralytics YOLOv5 workflows: detection, segmentation, classification, export, benchmarks, datasets, weights, and Flask REST serving.

VectorSpaceLab/AREX-Skill