Results for “lightgbm”

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

RGB protocol: client-side validated smart contracts on Bitcoin + Lightning. Schema-driven contracts, AluVM (RGB VM), rgb-lightning-node for LN integration. USDT-on-RGB rollout. USE WHEN: building RGB contracts, integrating RGB Lightning, comparing with TAP.

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

Train, fine-tune, and deploy LLMs using LitGPT's clean implementations of 20+ architectures like Llama, Gemma, and Phi.

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.

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.

Implements sibling communication between Lightning Web Components using Lightning Message Service (LMS) or the legacy pubsub utility, covering message channel definition, publish/subscribe patterns, and scope selection.

Generates OMG-compliant BPMN 2.0 XML and SVG diagrams from natural language process descriptions, with validation, automatic layout, and optional process optimization advisories.

GLaMM: Pixel Grounding Large Multimodal Model

Enables decoupled pub/sub messaging between ViewModels using CommunityToolkit.Mvvm Messenger, covering weak/strong references, request/reply patterns, channel tokens, and lifecycle management.

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

Compares 2-5 stocks or options across GBM Five Pillars scores, options metrics, technicals, and valuations, highlighting winners per category and providing an overall recommendation.

Generate and conversationally edit short videos with Google Gemini Omni Flash (`gemini-omni-flash-preview`). Use when: (1) iterating on a clip with natural-language edits instead of regenerating ("make the phone invisible, keep everything else the same"), (2) generating 3-10s 720p clips with synthesized audio, rendered on-screen text, or timecoded beats, (3) binding reference images to roles with <FIRST_FRAME>/<IMAGE_REF_N> prompt tags, (4) editing an existing uploaded video. Accessed via the `gemini_omni_video` tool using the project's GEMINI_API_KEY/GOOGLE_API_KEY — the same key as Imagen and Google TTS.

Liquid Network: federated sidechain by Blockstream. Confidential Transactions, asset issuance (LBTC, USDt-Liquid, others), 2-min blocks, n-of-m federation peg-out. Elements codebase. USE WHEN: building on Liquid, peg-in/peg-out integrations, designing CT-based privacy.

Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.

Use when adding a fixed full-screen WebGL laser background with a thin white-hot vertical core, restrained brand-colored halo, and soft smoky fog. Prefer this over mengto-corner-lasers when the beam is a full-viewport WebGL background, not corner ornaments; not for full page layout, copy, or unrelated particle systems.

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

Simulates profit and loss for option positions across underlying price, implied volatility, and time to expiration, generating diagrams, breakeven analysis, and probability distributions.

Turns a rough request into working software via a governed build loop: align first, plan, then iterate one task at a time with deterministic backpressure and holdout-scenario judging.

Quantize LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss using bitsandbytes. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

Build accessible modal dialogs in LWC using the LightningModal base class, covering open(), close(), sizes, and accessibility.

Builds input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs using NeMo Guardrails, Presidio, and Guardrails AI.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Create React loading, processing, selected, current, focus, and pressed states with the border-beam package's animated edge glow. Use when a card, button, input, tab, option, task panel, or agent surface needs a restrained traveling or breathing beam; includes installation, imports, prop selection, state wiring, reduced motion, accessibility, and performance and layout guardrails.

MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Detects unusual options activity and classifies smart money signals to help follow institutional positioning, including volume/OI ratio spikes, block trades, sweep orders, and net premium flow.

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Track key macro indicators (VIX, US10Y, DXY, gold, oil, BTC) and get AI-generated impact analysis linked to your portfolio holdings.