'model compression' 검색 결과

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

Configure prompt compression, which shortens text sent to AI models, through the OmniRoute command line. Adjust RTK filters, Caveman rules, and combined compression modes, then preview the results using real prompts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preview compression results with real prompts
• Adjust RTK filters and Caveman rules
• Compare combined compression modes

Convert language models to GGUF and reduce their size through quantization, which stores model weights at lower precision. Guides cover compression choices, local inference on CPUs and Apple Silicon, and integration with tools such as Ollama.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running a language model on a CPU-only computer
• Choosing model compression for available memory
• Configuring Metal acceleration on Apple Silicon

Convert LLMs to GGUF and reduce model size through quantization, which stores weights at lower numerical precision. Prepare models for CPU or Apple Silicon inference, compare compression levels, and integrate them with local AI tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing an LLM for CPU-only use
• Running a local model on Apple Silicon
• Comparing model size and quality across quantization levels

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

Guides LLM compression through pruning, which removes selected model weights. Covers Wanda and SparseGPT methods without retraining, accuracy comparisons, and structured weight patterns that can accelerate inference on compatible hardware.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Trying model compression without retraining
• Comparing accuracy before and after pruning
• Choosing between Wanda and SparseGPT

Compress large language model weights to four bits with AWQ, a method that uses model activation patterns to limit quality loss. Follow workflows for quantization, loading compressed models, and serving them with vLLM using less GPU memory.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running large language models with limited GPU memory
• Quantizing a model with domain-specific text
• Serving an AWQ model with vLLM

Compress large language models to 4-bit weights to reduce GPU memory use and accelerate inference. Covers loading compressed models, configuring quantization, and using Transformers or vLLM, with guidance on hardware requirements and backend choices.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running large models with limited GPU memory
• Compressing a model with domain-specific sample text
• Serving AWQ models with vLLM

Apply HQQ quantization, which stores language model weights using fewer bits without calibration examples. Covers precision settings, inference backends, saving compressed models, deployment with HuggingFace Transformers or vLLM, and further training with LoRA.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compressing a model without calibration data
• Comparing 4-bit and 2-bit quantization settings
• Running quantized models with HuggingFace Transformers or vLLM

CesiumJS models, glTF, and particle effects - Model, KHR_meshopt_compression, CAD glTF extensions, EdgeDisplayMode, ModelAnimation, ModelNode, ParticleSystem, emitters, GPM extensions. Use when loading compressed or CAD-style glTF/GLB models, controlling edge rendering, playing model animations, positioning particles, or working with geospatial positioning metadata.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Compress LLM weights using HQQ quantization, which stores weights with fewer bits without calibration datasets. Follow workflows for precision settings, model saving, inference integration, and LoRA fine-tuning of quantized models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compressing LLMs without calibration datasets
• Serving quantized models with vLLM or HuggingFace Transformers
• Comparing bit widths and inference backends

Compress large language models to 4-bit weights to reduce GPU memory needs and accelerate text generation. Covers loading compressed models, converting your own models, choosing settings, and preparing memory-efficient fine-tuning with transformers and PEFT.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run language models with limited GPU memory
• Convert your own model to 4-bit weights
• Compare compression settings for quality and speed

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Blender to web export workflows for 3D models and animations. Use this skill when exporting Blender models to glTF for web, optimizing 3D assets for Three.js or Babylon.js, batch processing models with Python scripts, automating Blender workflows, or creating web-ready 3D pipelines. Triggers on tasks involving Blender glTF export, bpy scripting, 3D asset optimization, model compression, texture baking, or Blender automation. Exports models for threejs-webgl, react-three-fiber, and babylonjs-engine skills.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design how an AI agent edits its own working conversation history, choosing what to retain, rewrite, or remove. Covers safeguards, capacity monitoring, recovery after overflow, and the computing cost of changing earlier context.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing agents that edit their own conversation history
• Preserving exact values during long tasks
• Recovering from context overflow

Reduza o tamanho de LLMs e acelere a inferência usando técnicas de pruning como Wanda e SparseGPT. Use para comprimir modelos sem retreinamento, alcançando 50% de esparsidade com perda mínima de acurácia, ou ativando inferência mais rápida em aceleradores de hardware. Cobre pruning não estruturado, pruning estruturado, esparsidade N:M, pruning por magnitude e métodos one-shot.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Rewrite lengthy prompts, tool descriptions, and agent instructions into compact text while preserving requirements, exceptions, and exact values. The process records removed content and compares token counts, the units models use to measure text length.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Shortening system prompts
• Compressing tool documentation and skill bodies
• Reducing text length for model input

Learn how instructions, documents, tool results, and conversation history form an AI model’s context. Understand attention limits, why information in the middle can be missed, and how relevance and placement inform decisions about what to include.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learning the basics of context engineering
• Understanding why more input does not always help
• Explaining how instruction placement affects attention

Prepare 3D models for browser games by cleaning source assets, exporting GLB or glTF, and optimizing geometry and textures. It also guides collision shapes, distance-based detail levels, and runtime checks for the chosen engine.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing Blender models for browser games
• Reducing GLB or glTF asset size
• Planning collision shapes and distance-based model detail

Audit a .glb or .gltf and make it small, correct, and fast to load in a browser, with a measured before/after report. Use when a model is "too big" or "slow to load", when the user asks to "optimize this GLB", "compress this glTF", or "export for web", or when they mention Draco, meshopt, gltfpack, KTX2, Basis, texture VRAM, draw calls, or a Blender / CAD / photogrammetry / Pascal export headed for Three.js, React Three Fiber (drei useGLTF), Babylon.js, or model-viewer. Covers inspection, spec validation, geometry and texture compression, scene-graph cleanup, and the correctness checks (metres, Y-up, node names, animations, PBR fidelity, alpha modes, vertex colors) that must not regress. Not for editing or modelling geometry, authoring or laying out a scene, generating 3D from text or images, converting from FBX/OBJ/CAD, or debugging a runtime frame rate that has nothing to do with asset size.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.