Results for “h200”

Selects the correct SageMaker serving container image URI for HuggingFace model deployments, prioritizing HuggingFace-curated Deep Learning Containers over generic alternatives.

GPU-aware PPO training configuration for A100/H100. Trigger when training is slow or GPU utilization is low.

Extract and preprocess tiles from whole-slide images (WSI) with histolab — OpenSlide-backed slide loading, tissue detection and masks, Random/Grid/Score tile extraction, and image/morphological filters for H&E preprocessing. Use when the user needs lightweight WSI slide preprocessing — building tile datasets for ML training, tissue segmentation, or quick tile-based inspection of histopathology slides. For end-to-end computational-pathology, deep-learning model training, nucleus segmentation, or multiplexed/spatial-proteomics (CODEX, Vectra) pipelines prefer alterlab-pathml instead. Part of the AlterLab Academic Skills suite.

Deploy and configure the Havoc C2 framework with teamserver, HTTPS listeners, redirectors, and Demon agents for authorized red team operations.

Fine-tune HuggingFace CV, VLM, or LLM models on local NVIDIA GPUs using an NGC PyTorch container, with support for full or LoRA training, dataset handling, and optional model push to the Hub.

Set up the Holoscan Sensor Bridge demo environment end-to-end: clone the repo, configure the host per platform, build and run the demo container, and verify connectivity to the sensor board.

Train or fine-tune language and vision models using TRL or Unsloth on Hugging Face Jobs cloud infrastructure, with support for SFT, DPO, GRPO, and reward modeling, plus GGUF conversion for local deployment.

Integrate a HuggingFace computer vision model into the NVIDIA TAO Toolkit ecosystem, covering the full pipeline from prerequisites to container testing.

Flash FPGA firmware on HSB Lattice boards and Leopard Imaging VB1940 cameras connected to NVIDIA devkits, with safety checks and multi-step upgrade/downgrade procedures.

Resolves, generates, and operates on media assets (audio, images, icons, logos, voice, color grades, LUTs) for HyperFrames projects, using a local cache and the HeyGen CLI for free-usage catalog search and TTS.

Turns a GitHub pull request into a code-change explainer video with changelog, feature reveal, or refactoring walkthrough built from the diff, commits, and files.

Build and operate a Havoc C2 framework for authorized red-team engagements, including team server deployment, evasive Demon agent generation, and post-exploitation.

Navigate the Ethereum L2 landscape: Arbitrum, Optimism, Base, zkSync, Unichain, and Celo. Covers how they work, deployment, bridging, and selection criteria, including 2025–2026 updates.

Connects AI assistants to the Hugging Face Hub via MCP server tools to search models, datasets, Spaces, and papers, retrieve repository details and documentation, run compute jobs, and use Gradio Spaces as AI tools.

Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterations on the wrong model. Calls `runcomfy run <vendor>/<model>/image-to-video` (or endpoint variant) through the local RunComfy CLI. Triggers on "image to video", "image-to-video", "i2v", "animate image", "make this move", or any explicit ask to turn a still into video.

Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends for deployment with vLLM or HuggingFace Transformers.

Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub

Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9 images, 3 videos, 3 audio — synchronized in-pass audio with natural lip-sync, cinematic motion refinement), the 4–15s duration schema, and when to route to HappyHorse 1.0 / Wan 2.7 / Kling instead. Calls `runcomfy run bytedance/seedance-v2/pro` through the local RunComfy CLI. Triggers on "seedance", "seedance 2", "seedance v2", "seedance pro", "bytedance video", or any explicit ask to generate video with this model.

【河图】SKILL.md — 全术数技能系统 v2.0

Designing GitHub Actions workflows in depth: trigger strategy, security hardening, performance optimization, PR automation, and Reusable Workflow design.

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

Operates Hetzner Cloud resources via the hcloud CLI, covering server, image, network, and load balancer management with read-only and write operations.

Digital pathology image processing toolkit for whole slide images (WSI). Use this skill when working with histopathology slides, processing H&E or IHC stained tissue images, extracting tiles from gigapixel pathology images, detecting tissue regions, segmenting tissue masks, or preparing datasets for computational pathology deep learning pipelines. Applies to WSI formats (SVS, TIFF, NDPI), tile-based analysis, and histological image preprocessing workflows.

Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.

Generates award-level UI with GSAP motion, bento grids, and Python-driven randomization for layout variety.

Estimates GPU memory required to load Safetensors or GGUF model weights for inference from the Hugging Face Hub using HTTP Range requests, without downloading weights locally.

Manage production secret infrastructure with HashiCorp Vault, cloud secret stores, automated rotation, and audit logging.

Deploy Meta's LlamaGuard moderation model to filter LLM inputs and outputs across 6 safety categories using HuggingFace, vLLM, or FastAPI.

HuggingFace hf CLI: search/download/upload models, datasets.

Inspect B20 token contract addresses on Base to verify factory recognition, initialization, policies, pause state, and risk flags via the public B20 Console API.

Measurement-driven model router for Claude Code. Routes Haiku/Sonnet/Opus per task class, logs every routed task with real $ numbers, and A/B tests cheaper tiers before you trust the savings.

BISON v2.0 — Conviction Holder (Hardened). Top 10 assets by volume. All signals are score contributors — no hard gates. Scanner enters via create_position internally (Wolverine pattern). RatchetStop exits. Thesis exit REMOVED. v2.0: every hard gate converted to score contributor, ensureExecutionAsTaker=false, conviction-scaled margin 25-37%.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

Globus CLI workflow for staging HuBMAP CODEX datasets from remote endpoints to HiPerGator