数据与 AI技能

Configure large language model pretraining with torchtitan across multiple GPUs. Covers ways to split training work, launch jobs on computing clusters, enable Float8 numerical processing, and save or resume training through distributed checkpoints.

中文简介正在准备中。当前显示英语简介。

• Pretraining Llama 3.1 8B on eight GPUs
• Configuring multi-node training with SLURM
• Enabling Float8 training on H100 GPUs

Guide large language model training with OpenRLHF using human preference feedback. Covers training method selection, distributed GPU setup, reward model training, and memory tuning, with examples for PPO, GRPO, and DPO.

中文简介正在准备中。当前显示英语简介。

• Choosing a training method for human preference alignment
• Setting up distributed training across multiple GPUs
• Training a reward model before PPO

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.

中文简介正在准备中。当前显示英语简介。

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

Fine-tune language models with TRL using GRPO, a method that compares scored responses to the same prompt. Covers training data, scoring functions, GPU-conscious settings, and monitoring for tasks with measurable correctness or required output formats.

中文简介正在准备中。当前显示英语简介。

• Train models to follow JSON or XML output formats
• Reward correct answers in math or coding tasks
• Balance correctness, format, and style during training

Adapt existing PyTorch training scripts to run across multiple GPUs or machines with Accelerate. This skill covers device setup, distributed training configuration, and mixed precision, which uses lower-precision numbers to reduce memory use.

中文简介正在准备中。当前显示英语简介。

• Adapt a single-GPU training script for multiple GPUs
• Configure mixed precision to reduce training memory use
• Set up training with DeepSpeed or FSDP

Add PyTorch FSDP2 to training scripts so model state can be split across GPUs. Covers distributed initialization, mixed precision, CPU offloading, and checkpoint saving and loading for models that exceed a single GPU's memory.

中文简介正在准备中。当前显示英语简介。

• Training a model that exceeds one GPU's memory
• Adding FSDP2 to an existing training script
• Configuring mixed precision and CPU offloading

Add safety checks to LLM applications with NeMo Guardrails. This skill guides input and output validation, detection of attempts to bypass safety rules, personal information masking, and checks for unsupported or inaccurate answers.

中文简介正在准备中。当前显示英语简介。

• Detect attempts to bypass an AI app's safety rules
• Mask personal information before processing
• Add fact-checking to generated answers

Get guidance on adapting LLMs through additional training with LLaMA-Factory. The skill covers a visual interface requiring no code, LoRA and QLoRA training methods, and documentation-based help with implementation, features, and debugging.

中文简介正在准备中。当前显示英语简介。

• Learning additional training through a visual interface
• Exploring LoRA and QLoRA training methods
• Checking supported models and multimodal features

Evaluate language models on knowledge, math, coding, safety, and image understanding benchmarks. The skill guides reproducible runs in containers using local Docker, Slurm clusters, or cloud execution, with shared configurations for model comparison and result export.

中文简介正在准备中。当前显示英语简介。

• Comparing models on the same benchmark tasks
• Running a small evaluation sample before a full benchmark
• Running large evaluations on a Slurm cluster

Explore training workflows that reduce harmful model responses using a written set of principles. The skill covers self-critique, revised training examples, and RLAIF, reinforcement learning from AI feedback, with implementation examples and hardware guidance.

中文简介正在准备中。当前显示英语简介。

• Designing principles for model safety training
• Creating training examples through self-critique and revision
• Planning reinforcement learning with AI-rated responses

Guides you through setting up RWKV, generating text, processing long documents in chunks, and fine-tuning models. Explains how to carry context between steps and compare memory use with Transformer models.

中文简介正在准备中。当前显示英语简介。

• Build streaming text generation
• Process long documents in chunks
• Plan RWKV fine-tuning

Prepare training datasets for large language models with GPU-assisted cleaning. Covers duplicate removal, quality filtering, and personal information redaction, with workflows for text, images, video, and audio using NeMo Curator.

中文简介正在准备中。当前显示英语简介。

• Clean web data for model training
• Remove exact and near duplicates from large text collections
• Redact personal information from training text

Build data processing pipelines for machine learning, from preprocessing to batch predictions. Uses Ray Data to handle datasets larger than memory, distribute work across CPUs and GPUs, and feed data into training frameworks.

中文简介正在准备中。当前显示英语简介。

• Preprocessing datasets larger than memory
• Running batch predictions across multiple GPUs
• Preparing image and tabular data for training

Helps adapt machine learning training to multiple GPUs and machines with Ray Train. Covers resource allocation, recovery from saved training states, and Ray Tune searches that compare settings such as learning rate and batch size.

中文简介正在准备中。当前显示英语简介。

• Adapt existing PyTorch training to multiple GPUs
• Run HuggingFace training across multiple machines
• Compare learning rates and batch sizes with Ray Tune

Set up, configure, update, and troubleshoot persistent memory for OpenClaw agents. The plugin stores conversations locally and supports automatic recall, task summaries, reusable skills derived from successful tasks, and a visual memory manager.

中文简介正在准备中。当前显示英语简介。

• Setting up persistent memory for OpenClaw
• Updating or troubleshooting the memory plugin
• Choosing local or external memory search models

Build Apache Spark pipelines for large datasets, including transformations, aggregations, and streaming analysis. Get PySpark or Scala code, partitioning strategies for dividing data across workers, and configuration advice to investigate slow jobs and resource usage.

中文简介正在准备中。当前显示英语简介。

• Build a pipeline to transform and aggregate large datasets
• Investigate slow Spark jobs and uneven data distribution
• Tune memory settings and data partitions

Adapt large language models to specific tasks through fine-tuning, or additional training. Prepares and validates datasets, configures LoRA or QLoRA to train a small subset of parameters, and supplies training settings, evaluation scripts, and deployment optimization guidance.

中文简介正在准备中。当前显示英语简介。

• Preparing and validating JSONL training data
• Choosing LoRA or QLoRA for available GPU memory
• Configuring training and monitoring overfitting

Build machine learning workflows that connect data checks, training, evaluation, and deployment. The skill implements experiment tracking, model version management, and automated retraining, with reproducible environments and explicit validation thresholds before models enter production.

中文简介正在准备中。当前显示英语简介。

• Automate model training and retraining workflows
• Record and compare machine learning experiments
• Build a feature store for model input data

Clean, combine, summarize, and reshape tabular data with pandas DataFrames, Python's table-like data structures. Produces transformation code and validation checks, including time series processing and memory-conscious approaches for large datasets.

中文简介正在准备中。当前显示英语简介。

• Fill missing values and correct data types
• Combine tables using multiple matching columns
• Create grouped summaries and pivot tables

Design and improve prompts for language models, then test their accuracy and consistency. Create reusable templates, JSON output schemas that define response structure, evaluation criteria, and test cases while considering token use and model differences.

中文简介正在准备中。当前显示英语简介。

• Designing prompts for a new AI application
• Improving inconsistent model responses
• Defining JSON response formats

Design and implement RAG systems, which retrieve documents to inform AI answers. Get document preparation strategies, vector database comparisons, combined keyword and meaning-based search, result reranking, and an evaluation plan for retrieval quality.

中文简介正在准备中。当前显示英语简介。

• Design an AI application that answers using internal documents
• Compare vector databases and document splitting strategies
• Improve search through keyword matching and result reranking

Turn books, transcripts, courses, and interviews into reusable agent skills. Extract practical frameworks and procedures, verify their source support, test representative tasks, and compile the results into a single entry or a skill pack.

中文简介正在准备中。当前显示英语简介。

• Turning a book's methods into reusable agent skills
• Extracting practical procedures from course or podcast transcripts
• Creating a single entry for studying and consulting source material

Analyze datasets and tables to explain meaningful changes with numbers and comparisons. Check data quality, distinguish supported findings from hypotheses, and recommend charts that help readers understand the results and make decisions.

中文简介正在准备中。当前显示英语简介。

• Comparing monthly sales trends
• Examining differences across regions or segments
• Measuring gaps against targets

Search Hugging Face Hub for models, datasets, papers, and AI apps. Inspect documentation, use hosted apps for image generation or transcription, and run or schedule code on cloud CPUs and GPUs through an MCP server connection.

中文简介正在准备中。当前显示英语简介。

• Compare models for a specific task
• Find training datasets
• Generate images or transcribe audio with Spaces