Model Training & Fine-tuning Agent Skills

Run GGUF models locally with llama.cpp, including finding the right file on the Hugging Face Hub, installing, quantizing, serving, and using Python bindings.

Instrument LLM applications with Langfuse for tracing, prompt versioning, evaluation, and dataset management across Python and JavaScript SDKs.

Explains machine learning model predictions using SHAP values, covering feature importance, visualization plots, model debugging, bias analysis, and production deployment.

Evaluates machine learning classifiers on their ability to distinguish signal from background in particle physics simulations, measuring how well algorithms rank signal events above background ones using the AUC metric.

Process large ML datasets in parallel across CPU or GPU clusters, with streaming execution, multi-format I/O, and integration with Ray Train, PyTorch, and TensorFlow for batch inference and preprocessing pipelines.

Evaluates geometric consistency in text-to-video generation by measuring structural and motion coherence across camera trajectories, detecting deformation and occlusion artifacts in static scenes.

Evaluates the throughput and resource allocation efficiency of RIS-aided mobile edge computing systems by measuring the total computation task bits successfully completed under varying network conditions.

Computes CIDEr and related metrics to score how well generated image descriptions align with human consensus, using reference sentences and triplet annotations.

Evaluates image captions by converting them into scene graphs and computing an F-score over semantic propositions, measuring how well a generated caption captures the meaning of an image compared to human references.

Pretrains large language models at scale using PyTorch-native torchtitan with 4D parallelism, Float8, and distributed checkpointing.

Benchmarks long-context language models across 20 sub-tasks spanning 3k–200k tokens, covering retrieval, reasoning, summarization, and instruction understanding, with exact-match accuracy as the primary metric.

Evaluates spatial realism and temporal flow consistency of AI-generated videos using embedding spaces and Fourier transforms, producing bounded STREAM-S and STREAM-T scores.

Measures inference latency of binarized, 8-bit, and 32-bit convolutional layers on edge devices to evaluate the efficiency and speedup of the Larq Compute Engine framework compared to standard implementations.

Computes Theil's U (uncertainty coefficient) between predictions and ground truth using the torchmetrics implementation, handling categorical data and NaN strategies.

Evaluates an AI judge system's pairwise ranking accuracy on generated commit messages against a heuristic ground truth from five automatic text metrics, using the MCMD dataset.

Benchmarks medical AI agents on synthetic EHR tasks, measuring success rates for data retrieval, temporal aggregation, and threshold-based conditional logic with exact-match scoring.

Benchmarks energy-function-based safe control algorithms on the BIS (Benchmark of Interactive Safety) dataset, scoring safety, efficiency, and hybrid performance in human-robot and robot co-working scenarios.