Model Training & Fine-tuning Agent Skills

Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology, including dataset creation, metric selection, failure analysis, and iterative improvement.

Manage machine learning models in the Agent Platform Model Registry: list, describe, upload, update, and delete models and their versions.

Manage Hugging Face Hub resources: download/upload models, datasets, spaces; manage repos, buckets, collections, discussions, and cache; run SQL queries on datasets; authenticate and manage tokens.

Estimates the memory required to load Safetensors or GGUF model weights for inference from the Hugging Face Hub, using HTTP Range requests without downloading weights.

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning) with support for SFT, DPO, GRPO, KTO, RLOO, and reward model training via CLI commands.

Queries Hugging Face benchmark leaderboards to find the best AI models for a task, filters by device constraints, and returns a ranked comparison table with scores.

Train or fine-tune language and vision models using TRL or Unsloth on Hugging Face Jobs cloud infrastructure, with support for SFT, DPO, GRPO, and reward modeling, plus GGUF conversion for local deployment.

Search the Hugging Face Hub for llama.cpp-compatible GGUF models, select the right quantization, and run them locally with llama-cli or llama-server.

Trains and fine-tunes vision models for object detection, image classification, and segmentation using Hugging Face Transformers on cloud GPUs, with automatic dataset validation and Hub persistence.

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware, with backend selection between vLLM, Transformers, and accelerate.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

Deploy, evaluate, fine-tune, and manage Microsoft Foundry agents end-to-end using Azure Developer CLI and MCP tools.

Walks users from a bare AKS cluster to a running AI model deployment, covering cluster verification, controller install, GPU assessment, provider setup, and first deployment.

Fine-tune models on Azure AI Foundry using SFT, DPO, or RFT, covering dataset preparation, training job submission, deployment, and evaluation.

Detect anomalies in time-series data using the Azure AI Anomaly Detector SDK for Java, with support for univariate and multivariate analysis, model training, and inference.

Segments abdominal organs from CT NIfTI volumes using the NV-Segment-CT VISTA3D model, producing label maps and structured evidence JSON.

Run automated hyperparameter optimization for NVIDIA TAO models using AutoMLRunner, supporting multiple search algorithms and experiment tracking.

Train, evaluate, export, distill, quantize, or run inference for a TAO DINO 2D object detector using transformer-based detection with denoising training and multi-scale features.

Trains, evaluates, exports, and runs inference for person re-identification models using TAO, learning discriminative embeddings for cross-camera matching.

Automates the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models, including baseline evaluation, RCA, synthetic defect generation, data mining, retraining, and deployment gating until KPI targets are met.

Submit and manage TAO training, evaluation, and inference jobs on SLURM GPU clusters over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed storage.

Trains, evaluates, exports, prunes, quantizes, retrains, and runs inference for OCDNet scene text detection models using TAO, detecting arbitrary-oriented text regions in natural images.

Trains, evaluates, exports, prunes, quantizes, retrains, and runs inference for TAO OCRNet models for scene text recognition from cropped text-region images, supporting CTC and attention-based decoders.

Train, evaluate, distill, quantize, export, and run inference for RT-DETR object detection models using NVIDIA TAO.

Fine-tune and deploy CLIP vision-language models for zero-shot classification, image-text retrieval, and embedding extraction with ONNX and TensorRT support.

Submit TAO jobs to Lepton managed GPU compute on DGX Cloud, with run/status/cancel interface and multi-node distributed training support.

Launch distributed Megatron-LM training jobs on a SLURM cluster with a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules, container conventions, monitoring, and per-rank failure diagnosis.

Plan, configure, and chain Nemotron model customization steps into single-step or multi-step pipelines for curation, translation, fine-tuning, RL alignment, benchmarking, checkpoint conversion, optimization, and evaluation.

Trains vision transformers via self-distillation without labels for self-supervised visual representation learning, and supports export and inference of NVDINOv2 backbones.

Trains, evaluates, exports, quantizes, and runs inference for Sparse4D multi-camera temporal 3D object detection and tracking models using TAO.

Collects launch inputs and runs preflight checks before executing TAO workflows such as AutoML, training, evaluation, inference, export, TensorRT engine generation, or DEFT jobs on supported platforms.

Trains, evaluates, and runs inference for BEVFusion multi-sensor 3D object detection models that fuse LiDAR and camera data in bird's-eye-view space for autonomous driving.

Train, evaluate, export, quantize, and run inference for a TAO OneFormer model that performs panoptic, instance, and semantic segmentation using task-conditioned queries.

Trains, evaluates, exports, quantizes, and runs inference for SegFormer semantic segmentation models using NVIDIA TAO.

Guides installing Earth2Studio via uv or pip, selecting model extras, and configuring environment variables.

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.