“llm”的搜索结果

Prepare an evaluation framework before fine-tuning a language model. Build labeled examples, checks for each failure type, and a base-model benchmark, while calibrating model-based judges against human labels to support comparisons after training.

中文简介正在准备中。当前显示英语简介。

• Build an evaluation set from agent traces
• Create separate checks for each failure type
• Calibrate an LLM judge against human labels

Investigate LLM application failures with Phoenix CLI by reviewing execution records, recording observations, and grouping mistakes into counted categories. Inspect datasets and experiments to identify which failure types deserve evaluation tests first.

中文简介正在准备中。当前显示英语简介。

• Investigating failures in LLM applications
• Grouping observed mistakes into failure categories
• Choosing which evaluation tests to build first

Set up Phoenix tracing for LLM applications in Python or TypeScript. The skill guides automatic and custom recording of individual operations, conversation grouping, metadata, feedback, and production settings such as batching and personal data masking.

中文简介正在准备中。当前显示英语简介。

• Set up tracing for an LLM application
• Record document retrieval and tool calls
• Group conversation traces by session

Guides background processing in Node.js and TypeScript with BullMQ and Redis. Covers job queues, which hold tasks for later execution, along with scheduling, priorities, rate limits, worker concurrency, and dependencies between processing steps.

中文简介正在准备中。当前显示英语简介。

• Design a queue for background tasks
• Schedule jobs for later or repeated execution
• Organize dependent steps into a job flow

Evaluate LLM application quality using automated scores, human reviews, and another language model as a judge. Compare models or prompts, establish baseline results, and detect quality drops through repeatable tests and statistical comparisons.

中文简介正在准备中。当前显示英语简介。

• Comparing models and prompts
• Checking quality before deployment
• Evaluating search quality in RAG applications

Diagnose failed model requests from OpenShell sandboxes to hosted APIs or local servers such as Ollama and vLLM. Check provider attachment, access rules, credentials, network layout, and client settings to identify the narrowest configuration change needed.

中文简介正在准备中。当前显示英语简介。

• Diagnose failed requests to hosted model APIs
• Troubleshoot connections to Ollama or LM Studio
• Investigate credential and endpoint mismatch errors

Run MNN checks and regression tests on a host computer or Android device, with stage summaries and failure logs. A separate workflow benchmarks LLM prompt processing and token generation on real iPhones and iPads, including branch comparisons.

中文简介正在准备中。当前显示英语简介。

• Run static checks and host regression tests
• Verify selected backends on an Android device
• Benchmark LLM speed and compare branches on iPhone or iPad

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.

中文简介正在准备中。当前显示英语简介。

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

Guides LLM training with verl using rewards to improve model responses. Covers data preparation, reward functions, GRPO and PPO configuration, distributed GPU training, and troubleshooting memory shortages or unstable training.

中文简介正在准备中。当前显示英语简介。

• Train math reasoning models with GRPO and answer-based rewards
• Configure PPO training with a separate value-estimation model
• Run large-model training across multiple GPU nodes

Manage AltLLM Portal API keys for external agents and applications through the local CLI. Covers creation, model access limits, disabling, and revocation, while documenting production failures that currently restrict working operations to listing and creating keys.

中文简介正在准备中。当前显示英语简介。

• List active and disabled API keys
• Create an API key for an external application
• Specify which models a new key can access

Manage wallet login for the local altllm CLI, including requesting a message to sign, verifying signatures from external wallets, checking saved session details, and removing the local session when logging out.

中文简介正在准备中。当前显示英语简介。

• Sign in using a wallet signature
• Log in with an external signer such as Privy
• Check the saved user and target URL

Check AltLLM Portal credit, expiry dates, billing transactions, and usage through the local altllm CLI. Review activity by period, model, or API key, and redeem promo codes using a saved Portal session.

中文简介正在准备中。当前显示英语简介。

• Check credit, expiry dates, and available models
• Review billing transactions by type
• Compare usage by period, model, or API key

Test LLM applications for malicious instructions, information leaks, and unsafe tool use. The skill runs attack cases and checks observable evidence, helping distinguish suspicious replies from reproducible failures with concrete impact.

中文简介正在准备中。当前显示英语简介。

• Test chat APIs for prompt injection
• Check document-based AI for hidden instructions
• Verify unsafe tool calls by an AI agent

Investigate Finelog logs and runtime measurements for Iris tasks, training, and vLLM. Discover available fields, write time-bounded SQL, summarize resource usage, compare central and regional records, and interpret counters correctly.

中文简介正在准备中。当前显示英语简介。

• Summarizing Iris task memory and CPU usage
• Comparing central and regional logs for forwarding delays
• Aggregating vLLM counters with reset handling

Choose LLM settings for theorem proving, code generation, and creative exploration. It provides examples for output limits and response variety, plus proof planning prompts and a method for generating multiple proof attempts and selecting the best candidate.

中文简介正在准备中。当前显示英语简介。

• Choosing LLM settings for theorem proving
• Adjusting output settings for code generation
• Increasing response variety for creative exploration

管理用于重复利用LLM回答的缓存，查看统计信息和已保存的内容，删除缓存或统计数据，并管理有效期及语义相似度阈值。

• 查看回答缓存统计
• 删除已保存的回答
• 调整缓存有效期

Design criteria for using an LLM to judge AI responses through scoring or comparisons between two answers. Includes checks for order and length bias, plus validation against human judgments to assess evaluation reliability.

中文简介正在准备中。当前显示英语简介。

• Build an automated evaluation pipeline for AI responses
• Compare responses after changing a prompt or model
• Define shared scoring criteria for reviewers

Create and run evaluations in Arize using an LLM as the judge. Define scoring criteria, connect them to actual data fields, evaluate recorded operations or experiment results, and set up continuous scoring for new data.

中文简介正在准备中。当前显示英语简介。

• Check answers for unsupported claims
• Score experiment results for correctness
• Continuously evaluate new production records

Inspect existing LLM application records in Arize to investigate errors, slow operations, or behavior changes. Export traces, which group related operations, or individual operations and conversation sessions as JSON using the ax command-line tool.

中文简介正在准备中。当前显示英语简介。

• Investigate errors in an LLM application
• Review the inputs and outputs of a conversation
• Find slow operations in recorded traces

Design and refine prompts for LLM applications by organizing roles, context, instructions, constraints, and output formats. Develop representative examples, manage the information supplied to the model, and evaluate changes to improve how consistently responses match expectations.

中文简介正在准备中。当前显示英语简介。

• Structuring a system prompt for an LLM application
• Specifying response formats and constraints
• Creating examples that include edge cases

Design RAG systems that retrieve relevant documents to support LLM answers. The skill guides document splitting, meaning-based and keyword search, result reranking, and separate retrieval evaluation to improve the context passed to the model.

中文简介正在准备中。当前显示英语简介。

• Designing document retrieval for LLM answers
• Reviewing document splitting strategies
• Combining keyword and meaning-based search

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.

中文简介正在准备中。当前显示英语简介。

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

Reduce LLM weight usage through pruning, which removes selected model parameters. Explore Wanda and SparseGPT for compression without retraining, choose hardware-friendly patterns for faster inference, and compare the compressed model's accuracy with the original.

中文简介正在准备中。当前显示英语简介。

• Compressing an LLM without retraining
• Comparing pruning methods
• Exploring faster inference on supported hardware

Prepare trained machine learning models for production with deployment, monitoring, and retraining workflows. Build RAG systems that retrieve documents for answers, and integrate language model APIs with retries, fallback providers, and cost tracking.

中文简介正在准备中。当前显示英语简介。

• Deploying a trained model to production
• Setting up model monitoring and retraining workflows
• Building a RAG pipeline for document-based answers