“distillation”的搜索结果

Guide knowledge distillation, where a smaller language model learns from a larger teacher. Covers training from teacher responses or prediction scores, adjusting training settings, and comparing outputs to support model compression and specialized training.

中文简介正在准备中。当前显示英语简介。

• Compressing a large language model into a smaller model
• Training a specialized model from teacher-generated examples
• Comparing distillation methods and training settings

Choose what kind of knowledge to transfer between teacher and student models: response, feature, or relational, and decide among offline, online, self, or cross-modal distillation schemes. Best for distillation strategy selection, capacity-gap diagnosis, and transfer planning. Activate on "knowledge distillation", "teacher-student", "soft labels", "feature distillation", "online distillation", or "cross-modal transfer". NOT for generic compression checklists or unrelated training work.

中文简介正在准备中。当前显示原文说明。

Train smaller language models using knowledge distillation, where a larger model supplies examples or prediction targets. This skill covers training losses, generated training data, parameter choices, and output comparisons to support model compression and specialized student models.

中文简介正在准备中。当前显示英语简介。

• Training a smaller model from a larger teacher
• Fine-tuning with teacher-generated responses
• Distilling domain knowledge into a specialized model

Design deployment-focused distillation systems that balance model size, accuracy, calibration, and cascade escalation under real resource limits. Best for teacher-student compression, threshold design, and failure-aware deployment. Activate on "model compression", "teacher- student", "distillation score", "cascade model", "edge deployment", or "model calibration". NOT for generic deep-learning overviews, prompt optimization, or training work without a concrete distillation objective.

中文简介正在准备中。当前显示原文说明。

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

中文简介正在准备中。当前显示原文说明。

Deep analysis of knowledge distillation techniques for compressing large models into smaller efficient ones

中文简介正在准备中。当前显示原文说明。

Comprima modelos de linguagem grandes usando destilação de conhecimento de modelos professor para aluno. Use ao implantar modelos menores com desempenho retido, transferir capacidades do GPT-4 para modelos de código aberto ou reduzir custos de inferência. Aborda escalamento de temperatura, alvos suaves, KLD reversa, destilação de logits e estratégias de treinamento MiniLLM.

中文简介正在准备中。当前显示原文说明。

SkillAlchemy — One thought conceived, one goal achieved. Accept any idea or distillation target and produce an installable SKILL.md. It uses Lens to clarify the problem and LEAP to run distillation or fusion. This is the sole user-facing entry point. Use when the user asks to distill, generate a skill, fuse skills, or says, "I want to build X, but I do not know where to start."

中文简介正在准备中。当前显示原文说明。

Expert-level separation processes covering distillation, absorption, extraction, crystallization, membrane separations, and adsorption for chemical engineering applications.

中文简介正在准备中。当前显示原文说明。

Use when the operator says "run distillation" or "refresh complexity corpus", or a distillation pass is due.

中文简介正在准备中。当前显示原文说明。

Set up and run knowledge distillation (on-policy, off-policy, or multi-teacher) from a teacher model to a student model using the Tinker API. Use when the user wants to distill knowledge, compress models, or train a student from a teacher.

中文简介正在准备中。当前显示原文说明。

Build training datasets for LLM specialization from production data, frontier model distillation, and synthetic bootstrapping. Use when formatting production logs into SFT data, distilling from frontier APIs, or preparing data for fine-tuning. Covers JSONL formatting, data quality validation, deduplication, and train/eval splitting.

中文简介正在准备中。当前显示原文说明。

根据参考视频测得的色彩与剪辑节奏，生成视频并与现有素材、叠加画面和三维道具合成，通过数值核对成片，同时交付可再次编辑的时间线。

• 按照参考视频的风格制作视频
• 为现有视频添加生成片段
• 合成叠加素材与三维道具

测量参考视频的色调与镜头时长，整理成可复用的风格素材包，包含用于颜色转换的LUT、静帧、叠加素材，以及供生成模型使用的规格说明。

• 将参考视频色调制成素材
• 测量剪切间隔以参考节奏
• 按类型建立风格素材库

使用ReasoningBank和AgentDB实现经验记忆：记录智能体的行动与结果，检索相似经历、评估结果并整理记忆，供后续决策复用。

• 开发能够复用经验的智能体
• 记录智能体行动并评估结果
• 将相似经历整理为共通模式

Build agent memory with ReasoningBank and AgentDB. Record actions and outcomes, retrieve similar experiences, assess results, and consolidate memories into reusable patterns so agents can draw on past work when making decisions.

中文简介正在准备中。当前显示英语简介。

• Build agent memory that reuses past experiences
• Record and assess sequences of agent actions
• Consolidate similar experiences into reusable patterns

Plan further training for AI agent models by diagnosing gaps in knowledge, output consistency, or decision making. Compare continued pretraining, supervised fine-tuning, reinforcement learning, and distillation, then design training data, feedback environments, and evaluation checks.

中文简介正在准备中。当前显示英语简介。

• Choosing a training approach for an agent model
• Designing training examples and source data
• Planning reward checks and reinforcement learning environments

Synthesize OpenViking knowledge bases or document collections into topic-based Markdown pages that explain trends, changes, comparisons, and implications. Keep conclusions traceable to source evidence, distinguish facts from inferences, and preserve disagreements and uncertainty.

中文简介正在准备中。当前显示英语简介。

• Comparing changes across financial reports
• Finding shared trends across knowledge bases
• Organizing sourced conclusions by topic

Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.

中文简介正在准备中。当前显示英语简介。

• Fine-tuning an embedding model for domain-specific search
• Training a model to rerank search results
• Training SPLADE or ColBERT retrieval models

Run batches of machine learning experiments on remote GPUs over SSH, varying settings and random seeds. The skill schedules jobs, tracks progress, retries GPU memory failures, and cleans up leftover sessions before starting subsequent batches.

中文简介正在准备中。当前显示英语简介。

• Run experiments across multiple random seeds
• Test combinations of model settings
• Chain teacher training and student distillation

Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.

中文简介正在准备中。当前显示英语简介。

• Fine-tuning an embedding model for domain-specific search
• Training a model to rerank search results
• Training SPLADE or ColBERT retrieval models

Build agent memory with ReasoningBank and AgentDB. Record actions and outcomes, retrieve similar experiences, assess results, and consolidate memories into reusable patterns so agents can draw on past work when making decisions.

中文简介正在准备中。当前显示英语简介。

• Build agent memory that reuses past experiences
• Record and assess sequences of agent actions
• Consolidate similar experiences into reusable patterns

[omh] Turn repeated lessons into written rules: extract repeated principles from skills, prompts, traces, reviews, and failures into reviewed rule candidates without auto-mutating guidance. Use when the user says: rules-distill, rules distill, distill rules, rule distillation, principle distill, skill principles, extract agent rules, turn traces into rules.

中文简介正在准备中。当前显示原文说明。

Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).

中文简介正在准备中。当前显示原文说明。