스킬 찾기

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Add descriptions for new models from the HuggingFace router to chat-ui configuration. Use when new models are released on the router and need descriptions added to prod.yaml and dev.yaml. Triggers on requests like "add new model descriptions", "update models from router", "sync models", or when explicitly invoking /add-model-descriptions.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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+ GPUs with Float8, torch.compile, and distributed checkpointing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Practical incident-response runbook for a suspected or confirmed ComfyUI / GPU-daemon compromise. Triage, scope, contain, forensic collection, weight-integrity verification, rebuild from clean snapshot, postmortem. NOT for hygiene scans on a healthy box (use supply-chain-defense-for-ml-extensions), and NOT for runtime hardening of a fresh deployment (use gpu-hosted-asset-hardening).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Import datasets from HuggingFace and convert them to Coval test sets. Use when the user wants to create test cases from HuggingFace dataset or repository.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Rebuild a degraded AI image to remove crunchy textures and repeated-edit artifacts while preserving identity, style, and composition. Use for clean remakes, not ordinary retouching or upscaling.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Vets third-party skills, plugins, MCP servers, GitHub Actions and model weights before install, with a verdict (PASS, CONDITIONAL, HOLD, FAIL) and install terms. Trigger on any should-I-install question, even with its files or hooks pasted in or a scan already clean; is this skill safe, vet this MCP server, check this GitHub Action, is this checkpoint safe or commercially usable, what does this installer write, a licence check before a fold-in, what changed in a plugin update; or say trustwarden (vet, revet, terms, refresh). Uses skillspector, zizmor, pinact and Scorecard when present; lists files no scanner read. Runtime permissions are gatewarden's; secrets shieldwarden's; your own skills skillwright's; sandboxing a download hypervrunner's.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plan, validate, and use 1Password CLI setup for secret injection and auth. Use when tasks need 1Password CLI usage, secret references, op run/read/inject, or provisioning secrets via env vars/.env files and scripts.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Reviews and approves blocked agent network requests in the TUI. Use when approving or denying sandbox egress requests, managing blocked network calls, or using the approval TUI. Trigger keywords - nemoclaw approve network requests, sandbox egress approval tui, customize nemoclaw network policy, sandbox egress policy configuration.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Work with state-of-the-art machine learning models for NLP, computer vision, audio, and multimodal tasks using HuggingFace Transformers. This skill should be used when fine-tuning pre-trained models, performing inference with pipelines, generating text, training sequence models, or working with BERT, GPT, T5, ViT, and other transformer architectures. Covers model loading, tokenization, training with Trainer API, text generation strategies, and task-specific patterns for classification, NER, QA, summarization, translation, and image tasks. (plugin:scientific-packages@claude-scientific-skills)

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AI基础设施实战——从GPU集群调度到模型推理部署的全栈实操指南。覆盖：昇腾/GPU统一调度、PyTorch分布式训练、vLLM推理部署、模型量化实战、LLMOps、GPU故障诊断、HuggingFace生态、MLOps流水线。触发词：AI基础设施、GPU、昇腾、训练、推理、vLLM、PyTorch分布式、模型部署、LLMOps、MLOps、集群调度、HuggingFace

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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+ GPUs with Float8, torch.compile, and distributed checkpointing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.