“instruction tuning”的搜索结果

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

Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.

中文简介正在准备中。当前显示英语简介。

• Train a model on instruction and response examples
• Align responses using preferred and rejected answer pairs
• Build a training pipeline using human feedback

Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.

中文简介正在准备中。当前显示英语简介。

• Train a model on instruction and response examples
• Align responses using preferred and rejected answer pairs
• Build a training pipeline using human feedback

Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.

中文简介正在准备中。当前显示英语简介。

• Studying language model architecture through readable code
• Fine-tuning a model on custom instruction data
• Configuring LoRA training for a single GPU

Build image-based conversations with LLaVA, an AI model that combines image understanding with language. Covers setup, model selection, image descriptions, follow-up questions, and memory-saving options for running models on a GPU.

中文简介正在准备中。当前显示英语简介。

• Building a chatbot that answers questions about images
• Generating image descriptions and captions
• Exploring a scene through follow-up questions

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.

中文简介正在准备中。当前显示英语简介。

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

Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.

中文简介正在准备中。当前显示英语简介。

• Studying language model architecture through readable code
• Fine-tuning a model on custom instruction data
• Configuring LoRA training for a single GPU

Set up and run supervised fine-tuning (SFT) on instruction or chat datasets using the Tinker API. Use when the user wants to do instruction tuning, chat fine-tuning, or supervised learning.

中文简介正在准备中。当前显示原文说明。

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

中文简介正在准备中。当前显示原文说明。

Use when adapting large language models to specific tasks, domains, or behaviors - covers LoRA, QLoRA, PEFT, instruction tuning, and full fine-tuning strategiesUse when ", " mentioned.

中文简介正在准备中。当前显示原文说明。

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

中文简介正在准备中。当前显示原文说明。

Train language models with SimPO using pairs of preferred and rejected answers. Configure preference training without a separate reference model, adapt settings for base or instruction models, and address unstable training, memory limits, or lost capabilities.

中文简介正在准备中。当前显示英语简介。

• Training a base model with preferred and rejected answers
• Further tuning an instruction model with preference data
• Adjusting training settings for math and code tasks

Adapt large language models to specific tasks using LoRA and QLoRA, methods that train a small set of added parameters. Get guidance on preparing examples, choosing training settings, evaluating outputs, and saving or merging trained adapters.

中文简介正在准备中。当前显示英语简介。

• Adapting models to specialized terminology and output formats
• Planning training with limited GPU memory
• Preparing instruction-response datasets

Create and maintain Claude Code skills with clear file structure and activation rules. Get guidance on hooks, which run at specific workflow events, plus troubleshooting, edit restrictions, and splitting detailed instructions into reference files.

中文简介正在准备中。当前显示英语简介。

• Creating a new Claude Code skill
• Tuning skill activation conditions
• Investigating missing or unwanted activation

Adjust how AI agents generate workflows in cc-wf-studio by reviewing node descriptions, examples, and misleading constraints. The skill guides minimal schema edits, format regeneration, and testing to address biased node choices.

中文简介正在准备中。当前显示英语简介。

• Investigating repeated selection of the wrong node type
• Revising node descriptions and workflow examples
• Checking for constraints the runtime does not enforce

Analyzes Claude Project context budget under the automatic-RAG-by-window model: knowledge files vs. threshold-exempt overhead (Skills, MCPs, CI, Memory). Two modes: Quick Diagnostic and Full Budget Audit. Use when user says "check my context budget," "how much context am I using," "is my project too big," "optimize my token usage," "tier my files," "optimize for RAG," "improve retrieval quality," "should I keep compressing," "am I over-compressing," "should I accept RAG mode." Also trigger on context pressure symptoms: "Claude forgets my instructions," "responses getting generic," "content not found in my knowledge files." Also use when a project audit scores Knowledge Architecture ≤ 3. Do NOT use for content placement decisions (use rootnode-memory-optimization if available), full project audits (use rootnode-project-audit if available), or behavioral tuning (use rootnode-behavioral-tuning if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on legacy models.

中文简介正在准备中。当前显示原文说明。

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

中文简介正在准备中。当前显示原文说明。

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

中文简介正在准备中。当前显示原文说明。

使用TRL指导语言模型进一步训练，使回答更符合指令或人的偏好。涵盖数据准备、训练方式选择、奖励模型训练与评估，以及内存不足和训练不稳定时的调整。

• 用回答示例训练模型遵循指令
• 用DPO学习回答偏好
• 构建使用奖励模型的RLHF流程

利用优选与非优选回答对，对大语言模型进行无需独立参考模型的追加训练。提供不同模型的配置示例，并指导调整训练参数、应对训练不稳定和显存不足。

• 使用回答偏好数据训练模型
• 进一步调整指令响应模型
• 调整数学与代码任务的训练配置

Evaluate improvements to Archify diagrams using actual outputs and agent work records. Compare accuracy, readability, and total delivery time to investigate layout, connection routing, diagnostics, and authoring guidance, then document what the evidence supports.

中文简介正在准备中。当前显示英语简介。

• Comparing diagram layouts and connection routes
• Investigating repeated diagram repair attempts
• Testing changes to authoring guidance

Improve LLM prompts using Arize production traces, evaluation results, and human feedback. Extract current instructions, identify recurring failures, revise the prompt, and compare experiments to measure changes in output quality and catch regressions.

中文简介正在准备中。当前显示英语简介。

• Improve a prompt using failed production traces
• Fix responses that use the wrong output format
• Review unsupported answers in retrieval-based responses

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

中文简介正在准备中。当前显示原文说明。

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

中文简介正在准备中。当前显示原文说明。