Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+...
7528 results
(49.9ms)
page 39 / 377
modal-serverless-gpu
0.00
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
mamba-architecture
0.00
State-space model with O(n) complexity vs Transformers' O(nΒ²). 5Γ faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2...
reviewing-ai-papers
0.00
Analyze AI/ML technical content (papers, articles, blog posts) and extract actionable insights filtered through enterprise AI engineering lens. Use when user provides URL/document for AI/ML...
youtube-downloader
0.00
Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p,...
nanogpt
0.00
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture...
axolotl
0.00
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
browser-tools
0.00
Interact with a web browser. Can start a browser, connect to it, evaluate JavaScript, make screenshots, read console logs and let the user select DOM elements. Use when interacting with unknown...
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...
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring...
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable...
nemo-curator
0.00
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16Γ faster), quality filtering (30+ heuristics), semantic deduplication, PII...
nemo-guardrails
0.00
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses...
llamaguard
0.00
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy....
create-hooks
0.00
Expert guidance for creating, configuring, and using Claude Code hooks. Use when working with hooks, setting up event listeners, validating commands, automating workflows, adding notifications, or...
algorithmic-art
0.00
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow...
ffuf-claude-skill
0.00
Web fuzzing with ffuf
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate...
improve-instructions
0.00
Analyzes conversation history to improve CLAUDE.md files. Use when you notice patterns in how Claude misunderstands requests, want to consolidate repeated guidance, or improve instruction clarity...
mcp-builder
0.00
Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate external services.