Orchestra Research

Set up W&B to record machine learning metrics and settings, visualize training progress, and compare experiments. Includes automated searches for training settings, version tracking for datasets and models, and shared reports for team collaboration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording and visualizing training metrics
• Comparing experiments with different training settings
• Automatically searching for better training settings

Combine specialized language models without retraining using mergekit. The skill explains how to choose merging methods, configure each model’s contribution, compare resulting variants, and prepare a merged model for evaluation and deployment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Combine math, coding, and conversation capabilities
• Compare model variants with different merge weights
• Choose a method for merging several models

Build LLM serving workflows that produce JSON or other required formats. The skill covers reusing computation for shared prompts, tool calls, and ongoing conversations, with examples for server setup and structured output.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extracting article details into JSON
• Building agents that call tools
• Reusing shared prompts across conversations

Creates figures for machine learning papers from draft text or experiment data. Extracts components for Gemini-generated diagrams, chooses suitable charts with matplotlib or seaborn, and adjusts colors, fonts, and export formats for publication.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn a method section into an architecture diagram
• Create comparison charts from experiment results
• Plot training loss and accuracy over time

Build image captioning, visual question answering, and text-based image search with BLIP-2. The skill guides model selection, batch processing, and memory optimization, with examples for understanding images without training for each specific task.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate captions for multiple images
• Build a question-answering system for images
• Search an image collection using text

Create conference slides from a research paper in Beamer PDF and editable PPTX formats. Adapt the outline to the talk length, select key figures, and add speaker notes with timing and transitions, plus an optional talk script.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a paper into slides for an oral presentation
• Preparing a short spotlight or poster talk
• Creating speaker notes and a timed talk script

Configure LLM inference and serving on NVIDIA GPUs with TensorRT-LLM. Covers quantization, which reduces numerical precision, batching requests during generation, and distributing models across GPUs to improve processing capacity and response times.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up an LLM server on NVIDIA GPUs
• Configuring FP8 or INT4 quantization
• Distributing large models across multiple GPUs

Deploy language model APIs and run batch generation with vLLM. Configure GPU memory use, quantization—lower precision model storage—and distribution across GPUs, then test response times and monitor how many requests the server handles.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deploying an OpenAI-compatible language model API
• Generating responses for a large set of prompts
• Fitting a large model into limited GPU memory

Document how a research or coding session evolved after the work is complete. The skill extracts decisions, experiments, failed approaches, and claims into ara/ files, distinguishing user statements from AI suggestions and actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Record the reasons behind research decisions
• Preserve failed experiments and their lessons
• Distinguish user decisions from AI suggestions

Track machine learning experiments with SwanLab by recording training settings, metrics, and media such as images and audio. Learn to compare runs, inspect training charts, and connect existing training code to local, cloud, or self-hosted dashboards.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing experiments with different training settings
• Viewing training metrics in a local dashboard
• Logging sample images and audio alongside metrics

Review Agent-Native Research Artifacts, structured research packages for agents, across six dimensions of research quality. Produce a JSON report with scores, strengths, severity-ranked findings, practical improvements, and an overall acceptance or rejection recommendation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing an ARA before publication
• Checking whether evidence supports research claims
• Assessing experimental methods and research records

Build AI agents by connecting workflow blocks in AutoGPT's visual editor. This skill covers multi-step automation, scheduled runs, webhooks that start work after external events, execution monitoring, and custom agent development.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build an AI workflow in a visual editor
• Start an agent when an external event occurs
• Run a multi-step workflow on a schedule

Guides building chatbots and tool-using agents with LangChain. Covers conversation history, model provider integration, and RAG, which retrieves relevant documents to inform answers, plus tracing to inspect application behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a chatbot that remembers conversation history
• Create document question answering with source references
• Build an agent that uses custom tools

Guides building AI applications that search documents before answering questions, an approach called RAG. Covers importing files and web data, creating searchable indexes, adding conversational interfaces, and evaluating whether answers match the retrieved material.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a question-answering system for internal documents
• Create a chatbot that remembers conversation context
• Search information across files, web pages, and databases

Reduce LLM generation delays with speculative decoding, which proposes tokens ahead of verification. This skill compares small draft models, Medusa, and Lookahead Decoding, with implementation examples, tuning guidance, and deployment using vLLM.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reducing response delays in chatbots
• Speeding up code generation
• Choosing a small model to draft candidate tokens

Generate embeddings, numerical representations of text or images, for meaning-based search, similarity comparisons, and document grouping. The skill guides model selection, multilingual processing, local execution, and integration with retrieval workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate document embeddings for RAG
• Find sentences with similar meanings
• Group documents by topic

Use Outlines to make language models produce data in a defined format. The skill covers extracting information into JSON, restricting classification labels, and applying Pydantic models, which define fields and data types, with local model backends.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extracting company or profile details into JSON
• Classifying text using a fixed set of labels
• Generating text that matches a specified pattern

Use LangSmith to record LLM application inputs, outputs, and timing, investigate failures, evaluate answers against test datasets, and monitor production usage. It also guides automated quality checks and analysis of token usage and costs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating failures in LLM applications
• Evaluating answers against test datasets
• Monitoring production latency and costs

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 image classification and search with OpenAI's CLIP by comparing images with text descriptions, without additional training. Includes batch processing, image-text matching, and category-based checks for potentially inappropriate images.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Classify images using text labels without additional training
• Search an image collection with natural-language descriptions
• Compare how closely images match text descriptions

Build image conversations with LLaVA, a model that connects image recognition with language. This skill guides setup, image descriptions, visual questions, and follow-up conversations, with examples for Python, command-line use, and a Gradio interface.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a chatbot that answers questions about images
• Write detailed descriptions of photos
• Ask follow-up questions about the same image

Guides adapting OpenPI robot models to custom datasets and serving them to produce actions from observations. Covers JAX and PyTorch training, checkpoint conversion, and troubleshooting for normalization statistics and GPU memory.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fine-tune OpenPI models on custom robot datasets
• Convert JAX checkpoints to PyTorch
• Serve policies for ALOHA, DROID, or LIBERO

Build workflows that extract structured data from LLM responses, check field types and values with Pydantic, and retry failed extractions. Includes examples for nested data, classification, and receiving results as they are generated.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extracting contact and company details from text
• Classifying articles into predefined categories
• Checking review analysis against validation rules

Turn papers, code, experiment logs, and notes into an ARA, a structured research package for AI agents. Organizes claims, evidence, verification plans, code stubs, and research decisions, then checks coverage and consistency across the generated files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Organize a paper and its code into a research package
• Link research claims to tables, figures, and verification plans
• Preserve failed approaches and research decisions