'transformer' 검색 결과

Otimiza atenção em transformers com Flash Attention para ganho de 2-4x em velocidade e redução de 10-20x em memória. Use ao treinar/executar transformers com sequências longas (>512 tokens), ao encontrar problemas de memória GPU com atenção, ou quando precisa de inferência mais rápida. Suporta SDPA nativo do PyTorch, biblioteca flash-attn, H100 FP8 e sliding window attention.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.

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.

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

언어 모델 내부 반응을 소수의 특징으로 분해해 학습한 개념을 조사합니다. 사전 학습 SAE 분석, 자체 SAE 훈련, 특징을 통한 출력 조정과 재구성 품질 평가를 안내합니다.

• 사전 학습 SAE로 특징을 조사합니다
• 특정 모델 층을 대상으로 SAE를 훈련합니다
• 입력 문장별 특징 반응을 비교합니다

로컬 실행이나 지속적 통합에서 발견한 Python 타입 검사 오류를 분류하고, 타입 좁히기와 주석 수정부터 재검증까지 진행합니다. 새로운 타입 검사 범위 추가도 다룹니다.

• 지속적 통합의 타입 검사 실패 수정
• None이 포함된 타입 오류 수정
• 타입 검사 대상 디렉터리 추가

Explain a trading model's prediction by ranking the input features that contributed to its signal. Returns a Markdown table and saves an attribution record with calculation settings, adding a digital signature when a signing key is available.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing which inputs drove a trading signal
• Saving signed records of model explanations
• Reproducing rankings with the same signal and seed

Test your understanding of a phase in AI Engineering from Scratch through eight multiple-choice questions. Receive a score, explanations for incorrect answers, and specific lessons to review before continuing your studies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking your understanding after completing a phase
• Assessing readiness for the next phase
• Finding lessons to review from incorrect answers

Screen AI application inputs and historical logs for prompt injection, where malicious instructions try to redirect the model. Combine pattern matching, text structure scoring, and a DeBERTa classifier to flag suspicious content and produce JSON results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Screening chatbot and AI agent inputs
• Checking external text used in retrieval-based AI applications
• Auditing historical interaction logs for injection attempts

Turn a written diagram request into a JSON specification and render a blueprint-style SVG. Create system architectures, request flows, state machines, or neural network diagrams as files for documentation, READMEs, posts, and slides.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a system architecture diagram to a README
• Illustrating request flows or data pipelines
• Creating a state machine diagram

Build Python workflows that constrain language model output using text patterns and grammar rules. Generate structured JSON, restrict classifications to allowed labels, extract information, and combine reusable generation steps with loops and tool selection.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate JSON with a defined structure
• Constrain date, email, and identifier formats
• Classify text using a fixed set of labels

Fine-tune large language models with LoRA and QLoRA while limiting GPU memory use. Guides training settings and adapter management, using small sets of task-specific weights that can be saved, switched, or merged into a base model.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fine-tuning an LLM with limited GPU memory
• Choosing LoRA settings and training layers
• Switching task-specific adapters on one base model

Use SAELens to train and analyze sparse autoencoders, which separate neural network activity into features that may represent recognizable concepts. Explore pretrained features, evaluate reconstruction quality, and investigate how individual features influence language model outputs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Exploring features with a pretrained SAE
• Training and evaluating a custom SAE
• Studying overlapping concepts in model activity

Compress large language models to 4-bit weights to reduce GPU memory use and accelerate inference. Covers loading compressed models, configuring quantization, and using Transformers or vLLM, with guidance on hardware requirements and backend choices.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running large models with limited GPU memory
• Compressing a model with domain-specific sample text
• Serving AWQ models with vLLM

Adapt machine learning training to run across multiple GPUs or machines with Ray Train. Covers changes to existing code, comparing training settings with Ray Tune, and saving checkpoints so training can resume after failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adapting existing PyTorch code for multiple GPUs
• Training HuggingFace models across multiple machines
• Comparing learning rates and batch sizes with Ray Tune

Build Python workflows that constrain language model output using text patterns and grammar rules. Generate structured JSON, restrict classifications to allowed labels, extract information, and combine reusable generation steps with loops and tool selection.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate JSON with a defined structure
• Constrain date, email, and identifier formats
• Classify text using a fixed set of labels

Guides experiments that change internal values in PyTorch models to test what causes their behavior. Uses pyvene to swap or remove activations, locate influential components, train interventions, and save experiments for reuse.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Locating model components that affect an answer
• Comparing outputs after swapping internal activations
• Training interventions to investigate causal structure

Helps fine-tune large language models with LoRA and QLoRA, methods that train small sets of additional parameters. Covers memory-conscious training, configuration choices, saving adapters, and switching task-specific adapters on a shared base model.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fine-tune a model with limited GPU memory
• Choose LoRA settings for a specific task
• Switch task-specific adapters on one base model

Choose a serving container for models deployed on SageMaker. Match the model type to a compatible image, retrieve its address from the AWS catalog, and check regional availability, CPU or GPU variants, and required host settings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a container for an LLM deployment
• Select images for embeddings and rerankers
• Check regional image addresses and GPU compatibility

Fine-tune vision models on custom images using Hugging Face Jobs cloud GPUs. Covers object detection, image classification, and segmentation—identifying image regions—with dataset validation, hardware selection, cost estimates, monitoring, and saving trained models to the Hub.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train an object detector on custom images
• Fine-tune an image classifier
• Adapt SAM/SAM2 to custom image masks

Evaluate Hugging Face Hub models using inspect-ai or lighteval, with local inference or a provider-backed option. Choose an inference engine, start with a small test, and switch engines when model compatibility requires it.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run benchmark evaluations on a local GPU
• Choose an evaluation framework and inference engine
• Check a small sample before a full evaluation

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer), local validation, and job export; use when the user names Hugging Face or preliminary source inspection identifies one Hugging Face owner, and not for manual PyTorch loops, Lightning, inference-only pipelines, deployment, or experiment workflows.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Predicts whether a DNA variant alters mRNA splicing using sequence-based deep-learning tools — SpliceAI (10kb context dilated CNN, clinical default), Pangolin (multi-tissue), MMSplice (modular per-region CNN with calibrated ΔPSI), SpliceTransformer/TrASPr (tissue-aware transformers), SpliceVault (empirical 300K-RNA lookup of likely mis-splicing outcomes), CADD-Splice (composite score). Applies the ClinGen SVI 2023 framework for ACMG/AMP variant interpretation (PVS1, PP3, BP4 evidence codes), HGVS splicing nomenclature (c.123+1G>A, c.123-3T>G, r.spl?), extended-window scoring for deep-intronic pseudoexons, tissue-specific predictions, branchpoint variant detection (BPHunter, LaBranchoR), and splice-switching ASO design. Use when interpreting splice impact of clinical variants, prioritizing VUS, identifying deep-intronic pathogenic variants, or designing ASOs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.