「model」の検索結果

Use when working on or testing imp-server and its HTTP APIs - OpenAI/Anthropic endpoints, /v1/chat/completions, /v1/messages, /v1/responses, SSE streaming, tool calling, json_schema/regex/GBNF constrained decoding, thinking/reasoning_content, cache_control/prefix cache, model loading and swapping, request priority, X-Request-Id, OTLP tracing / traceparent / Jaeger, /metrics, container env (IMP_SET), "server returns 404/garbage", API compliance. Do NOT use for CLI-only inference (imp-cli), kernel work (sm120-cuda-expert), or pure output-quality checks (check-degeneration).

日本語の概要は準備中です。原文の説明を表示しています。

Use when verifying that a model in the imp inference engine produces coherent output without repetition loops, token-stuck states, or state corruption across turns or streams. Triggers on "degenerates", "check degeneration", "repetition loop", "own own own", "stuck token", "empty content", "multi-turn regression", "does it still work", "NIAH", and after enabling CUDA graphs / changing forward pass / MoE routing / KV cache or KV dtype / GDN state or scan / sparse attention / PDL / speculation (MTP, n-gram) / ragged prefill / batched-decode kernels (smallm, producer quantize) / FA2 softmax.

日本語の概要は準備中です。原文の説明を表示しています。

Use when keeping imp's docs and config examples coherent after a change - updating docs/internals/ARCHITECTURE.md / README / docs/GOAL.md / docs/MODELS.md / docs/ROADMAP.md / imp.conf.example / CHANGELOG / MISSION_JOURNAL, or "is this doc stale", "document this change", "the example config is out of date", "the README says X but the code does Y", "add a roadmap ledger row". Do NOT use for layer/frontmatter/lint questions (docs-layers), structural code audits (codebase-audit), measuring perf or refreshing the perf baseline (benchmark-cuda), or the agent's private memory (MEMORY.md).

日本語の概要は準備中です。原文の説明を表示しています。

Use when imp outputs differ between two paths that should agree - chunk sizes, prefill vs decode, prefix-cache resend, two engines (imp vs llama.cpp vs HF), two builds or kernels - "output changes with chunk size", "first token differs", "logprobs moved", "which layer diverges", "who is right, imp or llama.cpp", "near-tie". Do NOT use for repetition loops or garbage output (check-degeneration), a new arch that loads wrong (add-model-arch), or perf (benchmark-cuda).

日本語の概要は準備中です。原文の説明を表示しています。

Use when working on imp's quantization formats, loaders, or dequant paths - GGUF Q4_0...Q8_0/Q*_K/IQ4/MXFP4, NVFP4 two-level scaling (Modelopt vs compressed-tensors layouts), FP8 E4M3, StorageTier, decode cache, KV-cache dtypes (auto/fp16/fp8/int8/int4/nvfp4/mxfp4), "which quant should I use", "which KV dtype", scale-factor layout, dequant kernel wiring, imp-quantize / AWQ, judging quant quality (PPL). Do NOT use for writing/optimizing GEMM/GEMV kernels (sm120-cuda-expert) or measuring quant perf (benchmark-cuda).

日本語の概要は準備中です。原文の説明を表示しています。

Primary router skill for broad .NET work. Classify the repo by app model and cross-cutting concern first, then switch to the narrowest matching .NET skill instead of staying at a generic layer.

日本語の概要は準備中です。原文の説明を表示しています。

Apply MCAF ML/AI delivery guidance for data exploration, feasibility, experimentation, testing, responsible AI, and operating ML systems. Use when the repo includes model training, inference, data science workflows, or ML-specific delivery planning.

日本語の概要は準備中です。原文の説明を表示しています。

Create or update an ADR under `docs/ADR/` for architectural decisions, dependency changes, data-model changes, or cross-cutting policy shifts. Use when the user asks to write, update, or document an ADR, record a design decision, capture architecture trade-offs, or justify a repo-wide technical policy.

日本語の概要は準備中です。原文の説明を表示しています。

Use the open-source free `CSharpier` formatter for C# and XML. Use when a .NET repo intentionally wants one opinionated formatter instead of a highly configurable `dotnet format`-driven style model.

日本語の概要は準備中です。原文の説明を表示しています。

ALIGN-video for Claude Code with independent Codex adversarial review. Create or revise a video through agent-authored code, rendering, editing and fresh-context audiovisual review, without image, video or music generation models. Use for reference-led animation, procedural films, motion design, explainers, construction replays, and continuing an existing coded-video project. Carries the work from reference study and animatic through a finished, reproducible film; supports explicitly requested self-review when appropriate.

日本語の概要は準備中です。原文の説明を表示しています。

ALIGN for paper figures — draw a method-overview figure as an executable p5.js program that replays its own construction in named stages, exports SVG, and improves through pixel-only cross-model review whose gate is 'explain the method back from the figure alone, and is it worth looking at'. The method sets the relationships the figure must show, the chosen visual identity sets how its marks look, a composition source lends arrangements; the method may be the source's own (意临) or yours in its arrangement (风格迁移). Not for one-shot raster image generation.

日本語の概要は準備中です。原文の説明を表示しています。

ALIGN-video for Codex. Create or revise a video through agent-authored code, rendering, editing and fresh-context audiovisual review, without image, video or music generation models. Use for reference-led animation, procedural films, motion design, explainers, construction replays, and continuing an existing coded-video project. Carries the work from reference study and animatic through a finished, reproducible film; supports explicitly requested self-review when appropriate.

日本語の概要は準備中です。原文の説明を表示しています。

ALIGN — Agentic Loop Image GeneratioN. Paint a subject in the craft of a reference artwork as executable p5.js, Canvas, SVG or another mark-based medium, replay that craft's real order of work, and improve it through pixel-only cross-model review. The reference fixes the craft; the subject may be the reference's own scene (千里江山图 → p5.js) or another (清明上河图 → 武汉). Not for one-shot raster image generation.

日本語の概要は準備中です。原文の説明を表示しています。

当用户分析复杂问题时只用了单一视角(如纯财务/纯技术/纯市场),或面对跨领域问题缺乏分析框架时激活。典型触发信号:用户说"我只懂XX方面""这个问题好像是XX问题"但明显只用了一个学科的解释。不适用于用户已经有成熟的多维度分析框架且正在有效使用的场景,也不适用于纯执行层面的简单任务。

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user wants Agnes AI text, image, or video generation and should execute it through the agnes-ai-cli command line instead of hand-writing raw HTTP requests.

日本語の概要は準備中です。原文の説明を表示しています。

Evaluates LP portfolio rebalancing pressure from denominator effects with over-allocation analysis and pace adjustment recommendations. Use when analyzing denominator effects, assessing LP allocation constraints, or modeling portfolio rebalancing.

日本語の概要は準備中です。原文の説明を表示しています。

Assesses marketplace dynamics with take rate analysis, liquidity metrics, supply/demand balance, and network effect strength. Use when evaluating marketplaces, analyzing take rates, or assessing network effect moats.

日本語の概要は準備中です。原文の説明を表示しています。

Assesses litigation outcome impact with settlement probability, damage range estimation, and stock price sensitivity analysis. Use when evaluating litigation catalysts, modeling legal outcomes, or analyzing litigation-driven opportunities.

日本語の概要は準備中です。原文の説明を表示しています。

Assesses conglomerate break-up activism with segment valuation, separation feasibility, and tax-free qualification analysis. Use when evaluating SOTP activism, analyzing break-up proposals, or modeling separation value.

日本語の概要は準備中です。原文の説明を表示しています。

Structures credit underwriting with financial ratio analysis, cash flow quality assessment, and downside scenario modeling. Use when underwriting credit, analyzing borrower quality, or writing credit opinions.

日本語の概要は準備中です。原文の説明を表示しています。

Evaluates SPAC de-SPAC transaction economics with sponsor dilution, redemption risk, PIPE analysis, and warrant impact. Use when analyzing SPAC deals, evaluating sponsor economics, or modeling de-SPAC outcomes.

日本語の概要は準備中です。原文の説明を表示しています。

Structures 100-day and long-term value creation plans with revenue growth, margin improvement, and capital efficiency initiatives. Use when building value creation plans, tracking improvement initiatives, or preparing operating partner reviews.

日本語の概要は準備中です。原文の説明を表示しています。

Evaluates rating agency methodology application with loss model inputs, correlation assumptions, and tranche-level credit assessment. Use when analyzing structured product ratings, comparing agency methodologies, or assessing rating sensitivity.

日本語の概要は準備中です。原文の説明を表示しています。

Deconstructs unit economics with CAC, LTV, payback period, gross margin, and contribution margin analysis. Use when analyzing unit economics, validating SaaS metrics, or assessing business model efficiency.

日本語の概要は準備中です。原文の説明を表示しています。