'checkpoint' 검색 결과

Ask a more capable agent for a concrete execution plan for complex work. Request ordered steps, dependencies, checkpoints, and verification methods, then have the requesting agent assess the plan and carry out the work itself.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Break complex work into actionable steps
• Plan changes across multiple modules
• Define checkpoints and completion criteria

Guides setup and operation of Lambda Labs GPU instances for machine learning training and inference. Covers SSH access, persistent storage, API automation, and multi-GPU or multi-node training, including how to retain checkpoints and terminate idle instances.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up a GPU instance for LLM fine-tuning
• Keeping datasets and checkpoints between sessions
• Automating instance launch and termination through the API

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

Manage shell commands and AI agent tasks through a shared gbrain job queue. Track progress, steer agents, pause or resume work, and coordinate parallel tasks, with guidance for long operations, completion reporting, and reusable stage checkpoints.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run scripts as monitored background jobs
• Coordinate parallel research by AI agents
• Redirect, pause, or resume an agent task

Review an executed business decision against its original success and stopping criteria. Compare actual results, revisit assumptions and dissenting views, and create a retrospective record with lessons and follow-up actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a decision at its 90-day checkpoint
• Assessing a decision when stopping criteria are triggered
• Examining why a major decision was reversed

Evaluate a driving agent on CARLA Leaderboard routes after checking the required setup. Select routes and repetitions, save driving scores and infractions, record runs, and resume interrupted evaluations from a saved checkpoint.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Smoke-test a Leaderboard setup on one route
• Evaluate an agent across validation routes
• Resume an evaluation after a crash

Guides setup and operation of Lambda Labs GPU instances for machine learning training and inference. Covers SSH access, persistent storage, API automation, and multi-GPU or multi-node training, including how to retain checkpoints and terminate idle instances.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up a GPU instance for LLM fine-tuning
• Keeping datasets and checkpoints between sessions
• Automating instance launch and termination through the API

Manage Hugging Face Hub through the hf command line tool. Download and upload models or datasets, organize cloud storage, manage authentication and local caches, run scheduled jobs, and deploy or maintain model inference services.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Download or publish models and datasets
• Sync training checkpoints to cloud storage
• Inspect and clean the local cache

Execute a development phase by grouping plans into waves, sets of tasks that can run together based on dependencies. Collect results, verify completion, and update progress, with options to run a selected wave or work sequentially with checkpoints.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Execute all plans in a development phase
• Run one wave to manage usage limits
• Execute only plans that address verification gaps

Design and run bounded procedures in environments where current conditions are uncertain. The skill separates agent judgment from precise tool actions, verifies each effect, and records checkpoints so interrupted work can resume from observed evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing procedures for environments with varying conditions
• Resuming interrupted operations from verified evidence
• Deciding whether an agent or ordinary code should control a procedure

Review and improve SKILL.md files using nine evaluation criteria and test prompts. Independent agents compare original and revised versions, while user checkpoints, version history, and result cards help track which changes are retained or rolled back.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assess skill quality without editing files
• Improve instructions in a specific SKILL.md
• Prioritize weaker skills for revision

Turn articles, notes, or code history into talk preparation materials, including angles, titles, scripts, slide drafts, and revision sheets. Coordinate the stages with user checkpoints, or run an individual stage again.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare a talk from articles or notes
• Build an experience report supported by Git history
• Develop a script after choosing an angle and title

Investigate past agent runs using recorded tool results, commands, and file changes. Distinguish observed events from inferred causes, replay recorded decisions, or compare models from the same checkpoint to examine failures and alternative outcomes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracing why a file was deleted or overwritten
• Finding the step that broke a build
• Replaying a recorded failure

View a dashboard for a social science research environment with 24 specialized agents. Check configuration, project stage, human review settings, and connection readiness for paper retrieval services and other research tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check research environment configuration
• Review project stage and human checkpoints
• Find missing API settings

Revise formulaic academic prose through staged vocabulary and structure edits while checking that citations, statistics, and technical terms remain intact. Choose sections and editing intensity, compare changes, and review progress before accepting the revised manuscript.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Revising formulaic wording in an academic draft
• Editing only the discussion and conclusion
• Checking that citations and statistics survive revisions

Finalize a completed Claude Octopus project by checking readiness, running a multi-AI security audit, recording lessons, archiving project state, and creating a Git checkpoint. Produce a delivery summary and mark the project as shipped.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finalizing a completed project for delivery
• Running a required security audit before delivery
• Recording project lessons for future work

Manage a production-critical Marin training run from launch checks through monitoring, recovery, handoff, and completion. Keep commands, code versions, checkpoints, saved training states, and final outputs tied to a durable run record.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Launch a production training run with verified settings
• Resume interrupted training from a complete checkpoint
• Monitor training progress and investigate failures

Review completed work and its process against the original goals and acceptance criteria. Identify specific problems, root causes, and actionable fixes, while checking external criticism against evidence and correcting valid issues.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review deliverables before handing them over
• Reflect on work at a project checkpoint
• Check criticism and address valid points

Structure PyTorch training code with PyTorch Lightning, separating model logic, data preparation, and training settings. Use templates and configuration examples to add checkpoints, experiment logs, and distributed training that runs across multiple GPUs or TPUs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Restructuring PyTorch code into LightningModules
• Building reusable data preparation pipelines
• Configuring training across multiple GPUs or TPUs

Set up the public CodonFM v1 repository and download public Encodon checkpoints. Use for requests to build or launch the CodonFM development container, configure local data/checkpoint mounts, verify GPU access, or download public Encodon 80M, 600M, 1B, or Cdwt-1B weights. Do not use for Decodon, Encodon 5B/10B, missense-aggregation, or codon-optimization setup because those implementations are not in the public repository.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint, cosmos defect generation, cosmos-predict2 defect, cosmos-anomalygen, cosmos predict2 finetune.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize, evaluate, or compose these into a pipeline. Do NOT use for frontend/dashboard/visualization work, generic ML advice, billing/access, or non-Nemotron coding tasks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Convert a grover_base checkpoint (encoder-only or encoder + vocab heads) into a hybrid checkpoint by adding a randomly-initialized cMIM decoder + latent_dist, then continue pretraining on the user's corpus as hybrid (vocab + contrast). Effectively kermt-continue-pretrain with a one-time ckpt-conversion step prepended.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Finetune a pretrained KERMT encoder on a labeled CSV. Validate the checkpoint and data, prepare features, and run containerized training. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Write model bundles, prepared data, logs, and trained models to user-selected host directories.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.