756 skills · sorted by relevance
Ajuste fino com eficiência de parâmetros para LLMs usando LoRA, QLoRA e 25+ métodos. Use ao fazer fine-tuning de modelos grandes (7B-70B) com memória GPU limitada, quando precisa treinar <1% dos parâmetros com perda mínima de precisão, ou para serviços multi-adapter. Biblioteca oficial do HuggingFace integrada ao ecossistema transformers.
The English summary is being prepared. Showing the original description.
Orientação especializada para fine-tuning rápido com Unsloth - treinamento 2-5x mais rápido, 50-80% menos memória, otimização LoRA/QLoRA
The English summary is being prepared. Showing the original description.
Implementa e treina LLMs usando LitGPT da Lightning AI com 20+ arquiteturas pré-treinadas (Llama, Gemma, Phi, Qwen, Mistral). Use quando precisar de implementações limpas de modelos, entendimento educacional de arquiteturas ou fine-tuning de produção com LoRA/QLoRA. Implementações em arquivo único, sem camadas de abstração.
The English summary is being prepared. Showing the original description.
Orientação especializada para fine-tuning de LLMs com Axolotl - configs YAML, 100+ modelos, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, suporte multimodal
The English summary is being prepared. Showing the original description.
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
The English summary is being prepared. Showing the original description.
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
The English summary is being prepared. Showing the original description.
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
The English summary is being prepared. Showing the original description.
LoRaWAN and sub-GHz (433 / 868 / 915 MHz) attack methodology — LoRaWAN ABP/OTAA join attack, network/session key reuse, frame counter replay, downlink injection on TTN/Helium-style networks, sub-GHz protocol replay (KeeLoq garage doors, fixed-code remotes, TPMS spoofing, smart plug telemetry), HackRF / RTL-SDR / Flipper Zero workflows, signal analysis with Inspectrum / Universal Radio Hacker, and reconstruction of proprietary packet formats. Use for LoRaWAN deployments (smart cities, asset tracking, industrial telemetry), or any wireless device using the unlicensed 433/868/915 MHz bands (garage openers, doorbells, IoT sensors, RC equipment).
The English summary is being prepared. Showing the original description.
Analyze single-cell RNA-seq data with Scanpy, from quality checks and normalization to cell grouping, exploratory marker genes, and plots. Bundled scripts also prepare sample-level count summaries and support conversion of R objects to h5ad.
Inspect supported local scientific files before modeling, summarize structure and missing values, and flag possible data leakage or outlier effects. Produces bounded aggregate reports with identifiers obscured and provides a structured analysis report template.
Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.
Run model training, fine-tuning, inference, and batch jobs on Modal’s cloud GPUs. Estimate hardware needs and cost, generate Python launch scripts, run or deploy workloads, monitor logs, and retrieve results without managing remote servers.
Configure and manage BrowserWing to create, save, and replay browser automation scripts. Use AI exploration to generate repeatable workflows, export scripts as SKILL.md files for agents, and diagnose service or execution problems.
Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.
Plan weekly LinkedIn content, draft posts and replies, review wording, and publish after approval. This collection of twelve skills also covers profile improvements, audience analysis, and team posting programs, with manual publishing available without setup.
Draft a LinkedIn post from a topic and audience, choosing among 20 opening and structure formulas by the response you want. Includes founder-focused angles, wording cleanup, optional visuals, and scheduling through Publora after approval.
Turn existing tweets, videos, blogs, or newsletters into LinkedIn posts while preserving their claims and facts. Rebuild the opening, paragraph structure, and closing prompt, review artificial phrasing, and publish through Publora after approval.
Browse, inspect, create, and update exploratory testing sessions in TestDino, where testers investigate behavior beyond fixed test steps. Filter sessions by assignee, release, tags, or status, then assign work or change a session’s state using its ID.
Use when generating sexy/NSFW or posed images with local Qwen-Image 2.1 — pose/NSFW LoRAs (tawsLoRa femaledVaginus, TheseAlpacas, posture-v3), pose transfer from an existing image, or exact pose control via VNCCS PoseStudio 3D pose library. Triggers: 性感姿势, 摆姿势, NSFW 出图, 换姿势, 姿势控制, pose transfer, pose lora, VNCCS, 人偶姿势, 姿势库. Independent of any general image-generation skill (which handles SFW text/edit/cutout work).
The English summary is being prepared. Showing the original description.
Train custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to train a WAN or Z-Image LoRA; covers local + RunPod setup, dataset prep, key params, and using the result in a ComfyUI workflow.
The English summary is being prepared. Showing the original description.
Train a custom anime LoRA on the ANIMA base model with Citron's local Gradio trainer (kohya sd-scripts), <6GB VRAM, character/style LoRAs; covers setup, dataset prep, training params, and using the result in the anima-base workflow
The English summary is being prepared. Showing the original description.
Train a character/identity LoRA locally on FLUX.1-dev via the comfyui-mcp train_* tools (GPU Docker + ostris ai-toolkit). Use when the user wants to train a LoRA of a person/character from their photos on the local GPU. Covers dataset prep, launch, monitoring, and using the result in ComfyUI. For WAN/Z-Image training via the ai-toolkit UI see ai-toolkit-trainer.
The English summary is being prepared. Showing the original description.
Build and publish a Gradio Hugging Face Space for a user-provided image or video LoRA, including pipeline selection and model-card settings. Use for LoRA demos; use huggingface-spaces for general Space work.
The English summary is being prepared. Showing the original description.
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image
The English summary is being prepared. Showing the original description.