Back to categories
Category

Agent Skills in category: ml-development

22 skills match this category. Browse curated collections and explore related Agent Skills.

implementing-llms-litgpt

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

large-language-modelslightning-ailoralqora
ovachiever
ovachiever
81

weights-and-biases

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

experiment-trackinghyperparameter-tuningmodel-registryvisualization
ovachiever
ovachiever
81

simpo-training

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

preference-alignmentllm-trainingoptimizationfine-tuning
ovachiever
ovachiever
81

senior-ml-engineer

World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.

mlopsmodel-deploymentfeature-storellm-integration
ovachiever
ovachiever
81

ray-train

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

training-orchestrationdistributed-computinghyperparameter-tuningscalability
ovachiever
ovachiever
81

mlflow

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

ml-pipelinesmodel-deploymentexperiment-trackingmodel-lifecycle
ovachiever
ovachiever
81

moe-training

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

moedeepspeedhuggingfacemodel-training
ovachiever
ovachiever
81

llama-factory

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

fine-tuningllamano-codeqLORA
ovachiever
ovachiever
81

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

reinforcement-learningfine-tuningtransformerstrl
ovachiever
ovachiever
81

axolotl

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

fine-tuningLoRAmultimodalLLM
ovachiever
ovachiever
81

mlx-dev

Write correct, idiomatic Apple MLX code for Apple Silicon ML. Use when working with MLX arrays, neural networks, training loops, lazy evaluation, unified memory, mx.eval, mx.compile, Metal GPU, memory optimization, quantization, or Apple Silicon performance. Covers critical API differences from PyTorch/NumPy, array indexing gotchas (lists must be mx.array, slices create copies), NHWC format for Conv2d, __call__ not forward(), float64 CPU-only, mlx-lm integration, and debugging patterns.

apple-siliconmetal-gpumemory-optimizationquantization
tkwn2080
tkwn2080
31

feature-engineering-kit

Auto-generate features with encodings, scaling, polynomial features, and interaction terms for ML pipelines.

feature-engineeringscalingpolynomial-featuresinteraction-terms
dkyazzentwatwa
dkyazzentwatwa
3

rag-systems

Build RAG systems - embeddings, vector stores, chunking, and retrieval optimization

embeddingsvector-storechunkingretrieval-augmented-generation
pluginagentmarketplace
pluginagentmarketplace
1

fine-tuning

LLM fine-tuning with LoRA, QLoRA, and instruction tuning for domain adaptation.

fine-tuningloraq-lorainstruction-tuning
pluginagentmarketplace
pluginagentmarketplace
1

deep-learning

PyTorch, TensorFlow, neural networks, CNNs, transformers, and deep learning for production

pytorchtensorflowneural-networkscnn
pluginagentmarketplace
pluginagentmarketplace
11

mlops

MLflow, model versioning, experiment tracking, model registry, and production ML systems

mlflowmodel-versioningexperiment-trackingmodel-registry
pluginagentmarketplace
pluginagentmarketplace
11

computer-vision

Build computer vision solutions - image classification, object detection, and transfer learning

computer-visionimage-classificationobject-detectiontransfer-learning
pluginagentmarketplace
pluginagentmarketplace
11

fine-tuning

LLM fine-tuning and prompt-tuning techniques

fine-tuningllmprompt-tuningmodel-training
pluginagentmarketplace
pluginagentmarketplace
1

Page 1 of 2 · 22 results