“model debugging”的搜索结果

Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Guides logging for PyTorch and TensorFlow, including weight distributions and performance profiling to investigate training problems and processing bottlenecks.

中文简介正在准备中。当前显示英语简介。

• Monitoring training loss and accuracy
• Comparing experiments with different training settings
• Inspecting weight and gradient distributions

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

Guides PyTorch model training and fine-tuning, from choosing architectures to configuring optimizers and learning rates. Provides troubleshooting steps for unstable loss and memory shortages, plus methods for improving GPU throughput and comparing experiments.

中文简介正在准备中。当前显示英语简介。

• Choose model architectures for the available data type and scale
• Configure optimizers and learning-rate schedules
• Investigate loss spikes, NaNs, and GPU memory shortages

Write and debug code for further training large language models with TRL. Match training methods to dataset formats, configure supervised or preference-based training, and set up reward functions through Python or the command line.

中文简介正在准备中。当前显示英语简介。

• Training a language model on example responses
• Training with preferred and rejected response pairs
• Debugging GRPO reward functions and batch settings

Pick an LM output format per (task x consumer x model) rather than by reflex: different formats carry different cognitive load (e.g. code-in-JSON makes the same model write worse code than plain-text+diff, while asking for prose when you need a typed object fails the other way). Use when designing or debugging an LM's output schema, choosing between plain text / diff / JSON / tool-call / grammar-constrained output, or when a model's quality drops after wrapping its output in a structured format.

中文简介正在准备中。当前显示原文说明。

Main app ViewModel patterns (ScopedViewModel, Hilt, StateFlow, triggerEvent, navArgs, savedState flows, events). Use when writing, editing, exploring, debugging, or reviewing ViewModels in the store management app. Covers navArgs, combine+asLiveData, sealed state hierarchies, custom events, init blocks, and companion object placement. NOT for POS (WooPos*) code — use the `pos` skill instead.

中文简介正在准备中。当前显示原文说明。

Use when working with Bentoml — bentoML model serving and packaging management. Covers service management, model packaging, deployment status, API testing, Bento building, and runner configuration. Use when packaging ML models for serving, deploying BentoML services, debugging inference issues, or managing model artifacts.

中文简介正在准备中。当前显示原文说明。

Expert guidance for designing, implementing, migrating, and debugging SwiftData persistence in Swift and SwiftUI apps. Use when working with @Model schemas, @Relationship/@Attribute rules, Query or FetchDescriptor data access, ModelContainer/ModelContext configuration, CloudKit sync, SchemaMigrationPlan/history APIs, ModelActor concurrency isolation, or Core Data to SwiftData adoption/coexistence.

中文简介正在准备中。当前显示原文说明。

Use when designing, running, or judging an experiment on a Syntropic137 workflow - comparing prompt variants, fan-out vs single agent, adversarial cross-model review, model selection (can Haiku do this job), phase splits, or tool grants. Trigger phrases include "run a workflow experiment", "A/B the workflow", "does fan-out help", "which model for this phase", "is this prompt better", "measure review quality", "why did the workflow do that". Do NOT use for a one-off workflow run that is just doing work, for authoring a workflow that is not being compared against anything, or for debugging a single failed execution (that is ordinary debugging).

中文简介正在准备中。当前显示原文说明。

通过日志和复现操作排查OpenClaw的模型通信、工具执行及响应流问题，并检查已保存的对话和附件，为修复原因与再次验证收集证据。

• 排查本地测试与真实服务的行为差异
• 确认模型实际可见的工具
• 调查响应流的延迟或中断

帮助您使用Unsloth，以LoRA和QLoRA微调语言模型，探索减少GPU内存占用的训练方式，并依据官方文档整理的参考资料查询功能与API、实现代码和排查错误。

• 开始使用LoRA或QLoRA微调
• 查询Unsloth功能与API
• 排查训练代码中的错误

Configure supervised fine-tuning for models that process images and text. Define which components remain unchanged, set LoRA adapters for updating selected model weights, choose image resolution limits, and investigate training runs whose evaluation results fail to improve.

中文简介正在准备中。当前显示英语简介。

• Configure training for an image-and-text task
• Decide whether to train vision layers
• Investigate training with flat evaluation scores

Get guidance on adapting large language models with Axolotl. Covers YAML configuration files, LoRA and QLoRA methods for training fewer parameters, distributed training settings, dataset formats, and debugging training code.

中文简介正在准备中。当前显示英语简介。

• Write YAML settings for model fine-tuning
• Explore training with LoRA or QLoRA
• Configure training across multiple GPUs

Get guidance on adapting LLMs with Unsloth, including implementation, API usage, and debugging. Covers LoRA and QLoRA, methods for adjusting models with fewer trainable parameters, with a focus on training speed and memory use.

中文简介正在准备中。当前显示英语简介。

• Learning how to fine-tune models with Unsloth
• Exploring LoRA and QLoRA for efficient training
• Implementing features using Unsloth APIs

Investigate difficult bugs by adding temporary logs to the actual execution path and reproducing the reported behavior. Analyze JSONL logs, which store one structured event per line, then fix the cause, verify regression tests, and remove debugging artifacts.

中文简介正在准备中。当前显示英语简介。

• Investigating bugs that occur only during manual use
• Tracing event order in streaming or concurrent operations
• Checking whether passing tests cover the reported bug

Write integration tests for core error processors by simulating API failures with a mock model. Check retry attempts, changes to conversation messages, and streamed responses, with guidance on test setup and diagnosing empty output.

中文简介正在准备中。当前显示英语简介。

• Check retries and message changes after API errors
• Diagnose empty output in streaming tests
• Verify unrelated errors pass through unchanged

Investigate difficult bugs through explicit hypotheses, targeted logs, and repeated checks against actual data. Keep an investigation journal to track findings, examine environment differences and leftover state, and confirm the root cause before applying a fix.

中文简介正在准备中。当前显示英语简介。

• Investigate a bug that survived an initial fix
• Trace tests that fail intermittently
• Compare local behavior with a user's report

Guides fine-tuning and evaluation of OpenVLA-OFT robot models that turn images and language into actions. Covers LIBERO simulation, ALOHA deployment, LoRA adaptation that updates a small set of parameters, and troubleshooting action scaling or configuration mismatches.

中文简介正在准备中。当前显示英语简介。

• Evaluate pretrained models in LIBERO
• Fine-tune robot action models with LoRA
• Deploy server-client inference for ALOHA

Test Omnigent’s Cursor SDK integration against a live local server. Build test agents, run real conversations, and check authentication, model selection, and tool connections while investigating empty responses or bridge processes left after shutdown.

中文简介正在准备中。当前显示英语简介。

• Test Cursor authentication and real responses
• Verify file operations and sub-agent delegation
• Investigate invalid models and empty output

Test Omnigent’s GitHub Copilot SDK integration on a live local server. Build test agents, run real conversations, and inspect authentication, model selection, tool connections, policy enforcement, and leftover processes to investigate integration failures.

中文简介正在准备中。当前显示英语简介。

• Checking Copilot authentication with a real conversation
• Testing model selection and tool connections
• Verifying sub-agent dispatch and policy enforcement

Test Omnigent’s native Pi integration using the real terminal interface and a local server. Verify messages sent through the web or API, recorded replies, interruption, session resumption, authentication, and model settings to investigate integration problems.

中文简介正在准备中。当前显示英语简介。

• Checking message delivery from the web or API to Pi
• Verifying replies appear in the server transcript
• Testing interruption, resumption, and tool policies

Test Omnigent’s Antigravity SDK integration against a live local server. Build test agents and run real conversations to check Gemini authentication, model selection, tool connections, and failures across the full execution path.

中文简介正在准备中。当前显示英语简介。

• Test authentication and real Gemini responses
• Verify tool connections and sub-agent delegation
• Investigate model selection failures

Review how an AI agent loads, retains, summarizes, and shares working information. This historical guide helps examine forgotten constraints, repeated actions, tool selection, and handoffs using context engineering practices published in 2024–2025.

中文简介正在准备中。当前显示英语简介。

• Reviewing information loaded at startup versus on demand
• Investigating repeated actions or forgotten constraints
• Planning summaries and persistent task notes

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

中文简介正在准备中。当前显示原文说明。