training▌
12 indexed skills · max 10 per page
nemotron-customize
nvidia/skills · nemotron
Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize, evaluate, or compose these into a pipeline. Do NOT use for frontend/dashboard/visualization work, generic ML advice, billing/access, or non-Nemotron coding tasks.
performing-soc-tabletop-exercise
mukul975/Anthropic-Cybersecurity-Skills · performing-soc-tabletop-exercise
Performs tabletop exercises for SOC teams simulating security incidents through discussion-based scenarios to test incident response procedures, communication workflows, and decision-making under pressure without impacting production systems. Use when organizations need to validate IR playbooks, train analysts, or meet compliance requirements for incident response testing.
implementing-anti-phishing-training-program
mukul975/Anthropic-Cybersecurity-Skills · implementing-anti-phishing-training-program
Security awareness training is the human layer of phishing defense. An effective anti-phishing training program combines regular simulations, interactive learning modules, metric tracking, and positiv
ml-model-training
aj-geddes/useful-ai-prompts · AI/ML
Training machine learning models involves selecting appropriate algorithms, preparing data, and optimizing model parameters to achieve strong predictive performance.
sparse-autoencoder-training
davila7/claude-code-templates · AI/ML
SAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing polysemantic neural network activations into sparse, interpretable features. Based on Anthropic's groundbreaking research on monosemanticity.
training-llms-megatron
davila7/claude-code-templates · AI/ML
Megatron-Core trains LLMs from 2B to 462B parameters with up to 47% Model FLOP Utilization on H100 GPUs through advanced parallelism strategies.
moe-training
davila7/claude-code-templates · AI/ML
Use MoE Training when you need to:
nanochat-llm-training
aradotso/trending-skills · AI/ML
Skill by ara.so — Daily 2026 Skills collection.
openclaw-rl-training
aradotso/trending-skills · AI/ML
Skill by ara.so — Daily 2026 Skills collection.
openrlhf-training
davila7/claude-code-templates · AI/ML
OpenRLHF is a Ray-based RLHF framework optimized for distributed training with vLLM inference acceleration.