Results for “tomba”

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

Train and run Mamba state-space models with O(n) complexity, achieving faster inference and longer context than Transformers.

Search movies and TV shows, retrieve cast, ratings, streaming availability, and personalized recommendations via the TMDb API.

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.

Run TAO SDK jobs as Docker containers on a local or remote Docker daemon with NVIDIA GPU support, including preflight checks and credential handling.

Submit and manage TAO training, evaluation, and inference jobs on SLURM GPU clusters over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed storage.

Train, evaluate, export, quantize, and run inference for a TAO OneFormer model that performs panoptic, instance, and semantic segmentation using task-conditioned queries.

Fine-tune, evaluate, run inference, and export Cosmos-Embed1 video-text embedding models for tasks like text-to-video retrieval and semantic deduplication.

Train, evaluate, export, quantize, and run inference on Mask2Former models for panoptic, instance, and semantic segmentation using NVIDIA TAO.

info-to-ink

Intercepts responses to let users choose the depth and token budget before answering, with heuristic token estimation and preset depth levels.

Uruchamianie i wdrażanie platformy Soneta (enova365, Triva) w kontenerach. Używaj gdy użytkownik: (1) stawia środowisko (server + web) na obrazach Soneta przez `docker compose` albo na Apple `container` / Container Desktop; (2) tworzy bazę danych w kontenerze (usługa init z `dbmgr create`, `--demo`, `--recreate`, licencja, konwersja); (3) wdraża na Kubernetes przez Helm (`helm repo add soneta`, `values.yaml`, `dblist`, `adminMode`); (4) wybiera wersję obrazów (tagi z Docker Hub `soneta/*` lub `registry.soneta.pl`), architekturę (alpine/arm64/amd64), logowanie do registry; (5) potrzebuje SQL Servera — zewnętrznego (`host.docker.internal` / `host.containers.internal`) albo jako kontener `mssql`; (6) rozwiązuje problemy startu stacku (kolejność, port zajęty, brak DNS między usługami w Apple container, zły host-alias). Słowa kluczowe: docker compose, docker-compose.yaml, apple container, Container Desktop, helm, kubernetes, obraz, tag, wersja, mssql, dbmgr, x-init, server.standard, web.standard.

Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.

Detect abuse of legitimate Windows binaries (LOLBins) like certutil, regsvr32, mshta, and rundll32 using process telemetry, Sigma rules, and parent-child process analysis.

Captures tasks, projects, reminders, and commitments into a local-only personal execution engine, then recommends the best next action and tracks momentum.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Perform forensic on-chain analysis of EVM tokens to detect scams, rug pulls, and soft rugs by cross-referencing on-chain state against team narratives.

Volume-based PUMP token reward system with day-indexed epochs, pro-rata distribution, accumulator tracking, and cross-program claiming on Solana.

Turn a chosen design direction into a canonical DESIGN.md plus production tokens that don't look vibecoded — state-level colors (8-step neutral ramp, rest/hover/active/ disabled, focus ring), APCA-checked contrast, typography, spacing/radius/motion/elevation, an icon strategy, and component contracts for the core atoms. Emits tokens in the project's stack format (shadcn HSL vars or Tailwind v4 @theme). Load when the user asks to build a design system, generate design tokens, create a DESIGN.md, set up a theme, design a color or type system, pick icons, or when frontend-design routes here. Replaces design-tokens-craft and icon-craft. Sub-skill of frontend-design. Reads DIRECTION.md first.

MAMBA v2.0 — Range-bound high water + regime protection. A trading strategy config override based on the VIPER skill with three protective gates: BTC regime filter, per-asset cooldown after losses, and hard leverage cap at 10x.

Expert guidance for distributed NoSQL databases (Cassandra, DynamoDB). Focuses on mental models, query-first modeling, single-table design, and avoiding hot partitions in high-scale systems.

Use when the user explicitly enters TURBO, mode TURBO, enable TURBO, or TURBO for this task, and Codex should optimize for maximum quality without normal token-cost restraint.

Project Lombok for reducing Java boilerplate. Covers annotations for getters, setters, constructors, builders, logging, and more. Based on production patterns from castellino and gestionale-presenze projects. USE WHEN: user mentions "lombok", "@Data", "@Builder", "@Slf4j", asks about "boilerplate reduction", "getters/setters", "@RequiredArgsConstructor", "@Value" DO NOT USE FOR: Java language features - use `java` skill instead DO NOT USE FOR: MapStruct integration - use `mapstruct` skill DO NOT USE FOR: Spring annotations - use `backend-spring-boot` skill

Local text-to-speech via sherpa-onnx (offline, no cloud)

llama.cpp local GGUF inference + HF Hub model discovery.

Builds and governs design systems with a three-layer token architecture, component specs, and design-to-code handoff, including slide generation.

Design a theming architecture that supports brand variants, dark mode, and high-contrast modes with token mapping.

Arti — pure-Rust implementation of the Tor anonymity network, by Tor Project. Embeddable Tor client (no system Tor daemon needed), provides SOCKS proxy and programmatic API for connecting to .onion services or routing clearnet traffic through Tor. Used by privacy-respecting wallets (BHODL-style), messenger apps, and any Rust app needing anonymity. Ships as library (arti-client crate) or standalone CLI. USE WHEN: user mentions "arti", "Tor in Rust", "embedded Tor", "arti-client", "Tor circuit Rust", "onion service Rust", "TorClient", "BridgeConfig", "PreferredRuntime" DO NOT USE FOR: Bitcoin Core + Tor configuration - use `bitcoin/privacy/tor` DO NOT USE FOR: Browsing via Tor Browser - end-user tool, not dev DO NOT USE FOR: TLS configuration - use `network/rustls`

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

Design system implementation in Sage/Tailwind v4 — Figma to @theme tokens, design tokens CSS, Tailwind v4 @theme, color tokens, typography tokens, spacing scale, Blade UI components, kitchensink page, design-to-code, @layer base @layer components, CSS custom properties, resources/css/app.css, Paper MCP, Figma MCP, design file to code, SVG icons, responsive layout, design system audit, UI component library, atom design, layout components

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Total productive maintenance tracker

Generate and manage Terraform/Pulumi infrastructure configurations.

Transforms content into the cinematic, vernacular voice of Tom Waits, grounding abstractions in concrete imagery and finding dignity in the downtrodden.

Literature survey and SOTA tracking specialist. Use when the user asks to talk to Sova, requests the research tracker, or needs literature review, citation mapping, and paper analysis.