“model compression”的搜索结果

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。

Hermes Agent (Nous Research の AI CLI エージェント)。インストール、 CLI コマンド (chat, model, gateway, config, cron, webhook, mcp, skills, profile, hermes pm)、 Configuration (Terminal Backends, Memory, TTS / STT, Auxiliary Models, Compression, Display, Local Models llama.cpp, Egress / Secrets)、 Features (Tools, Skills, Hooks, Delegation, Kanban, Cron, Voice Mode, Personality, Context Files)、 Messaging Gateway (Platform Support, Bot Mode, Connectors)、Security、Architecture、 Hermes Desktop、Plugin Catalog、Profiles、Developer Guide、Nous Portal (Tool Gateway)。

中文简介正在准备中。当前显示原文说明。

Improve workflows involving multiple AI agents by measuring bottlenecks, adjusting workload distribution, and managing model costs. This design guide helps compare changes against a measured baseline while checking quality, latency, and resource use.

中文简介正在准备中。当前显示英语简介。

• Finding bottlenecks in workflows involving multiple agents
• Reviewing task distribution and parallel execution
• Reducing model costs within quality thresholds

Write and edit system prompts, tool instructions, and agent definitions with clear structure and explicit rule strength. It guides tag use, placement of critical constraints, concise wording, and practical examples that show how tools should be used.

中文简介正在准备中。当前显示英语简介。

• Drafting system prompts for agents
• Clarifying required and optional instructions
• Writing tool explanations with runnable examples

Audit instructions and memory files loaded on every agent turn. Identify repeated rules, contradictions, outdated content, and material better moved into skills, then receive evidence-backed recommendations ranked by estimated token savings and change risk.

中文简介正在准备中。当前显示英语简介。

• Reduce the size of instructions loaded on every turn
• Find conflicting rules across instruction and memory files
• Identify workflow instructions to move into separate skills

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

中文简介正在准备中。当前显示原文说明。

Design cost reduction strategies — model tiering, prompt compression, caching, batch inference. Use when asked to "reduce our AI costs", "set up model tiering", or "cut LLM spend".

中文简介正在准备中。当前显示原文说明。

Compressive Vasomotion Hypothesis (CVH) — vasomotion as a fast compression sweep that collapses ambivalent neural resonances (the Bayesian-blur problem) into a definite state. Use when modeling the ~100ms taṇhā 'grab', precision-weighting as compression forcefulness, or the generative collapse step of vasocomputational active inference.

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。

Formato GGUF e quantização llama.cpp para inferência eficiente em CPU/GPU. Use ao implantar modelos em hardware de consumidor, Apple Silicon, ou quando precisar de quantização flexível de 2-8 bits sem requisitos de GPU.

中文简介正在准备中。当前显示原文说明。

Quantização Half-Quadratic para LLMs sem dados de calibração. Use ao quantizar modelos com precisão 4/3/2-bit sem necessidade de conjuntos de calibração, para workflows de quantização rápida, ou ao fazer deploy com vLLM ou HuggingFace Transformers.

中文简介正在准备中。当前显示原文说明。

Expert en optimisation des coûts d'agents IA (sélection modèle, caching, compression prompts, budgeting tokens)

中文简介正在准备中。当前显示原文说明。

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

中文简介正在准备中。当前显示原文说明。

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

中文简介正在准备中。当前显示原文说明。

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

中文简介正在准备中。当前显示原文说明。

Treat tokens as a coding swarm's cost-of-goods-sold and legibility engine while accounting for finite subscription allowance when per-call price is unknown. Covers provider windows, remaining-usage evidence, burn forecasts, preemptive checkpoint/model switching, per-agent budgets, compaction, shared digests, context degradation, and spend metering. Activate on: "token budget", "context budget", "compaction strategy", "briefing as compression", "context rot", "summarization collapse", "COGS for agents", "subscription usage remaining", "five-hour or weekly limit", "burn forecast", "model switch before limit", or "/context-economics-for-agent-swarms". NOT for: memory architecture (use always-on-agent-architecture), single-prompt wording (use prompt-engineer), mechanism-design proofs (use nisan-et-al-2007-algorithmic-game-theory), physical containment (use sandboxed-adversarial-test-harness), or production rebodiment and fencing (use agent-resurrection-and-body-continuity).

中文简介正在准备中。当前显示原文说明。

Plan and improve AI agent systems by managing the information models receive. This collection covers memory, agent coordination, tool design, context compression, evaluation, and the operating controls needed for reliable autonomous workflows.

中文简介正在准备中。当前显示英语简介。

• Planning information management for a new AI agent
• Investigating failures in long agent conversations
• Designing agent memory and multi-agent coordination

Use when revising an ACM CCS paper for a precise threat model, calibrated attack/defense claims, 12-page ACM sigconf compression, double-blind wording, adaptive-evaluation honesty, and the security house style that survives an adversarial SIGSAC program committee.

中文简介正在准备中。当前显示原文说明。

Think and work like an expert HVAC Engineer. Use when a task calls for HVAC Engineer judgment. Reasons from psychrometric state, parallel heating and cooling load paths, and vapor-compression thermodynamics through TRACE/HAP and EnergyPlus load models, ASHRAE 62.1/55/90.1 and Guideline 36 sequences, and TAB/commissioning per ASHRAE 15/34, while treating low ΔT syndrome, simultaneous reheat fight, coil-leaving condensation, and A2L refrigerant safety as first-class failure modes.

中文简介正在准备中。当前显示原文说明。

Use when adding, importing, moving or loading textures, models, audio or scenes - per-platform compression, atlases, LODs, async loading per engine, engine metadata files (.meta, .import, .uid, .uasset), Git LFS, and asset validation tests.

中文简介正在准备中。当前显示原文说明。

Use when loading glTF/GLB models or textures in PlayCanvas, choosing Draco or Basis/KTX2 compression, or setting up decoders and preloading.

中文简介正在准备中。当前显示原文说明。