Results for “lepton”

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Diagnose monogenic and syndromic obesity in children and adolescents using a structured step-by-step algorithm. Use this skill whenever a clinician suspects a genetic cause of obesity, asks about leptin deficiency, MC4R mutation, POMC deficiency, PCSK1 deficiency, leptin receptor deficiency, Bardet-Biedl syndrome, Prader-Willi syndrome, Alström syndrome, or any case of early-onset severe obesity with hyperphagia. Also trigger for questions about targeted pharmacotherapy including setmelanotide or metreleptin, or when to order a genomic obesity panel. Cross-references the NHS Genomic Test Finder skill to surface the relevant R-code once a diagnosis is reached.

Extract Jetson Linux BSP and sample-rootfs tarballs, run apply_binaries.sh with the correct GPU stack flag, and record the image metadata in the active target profile.

Captures a read-only health snapshot from a Jetson device, reporting identity, memory, GPU, thermal, power, storage, services, and top processes.

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

Reduce per-token latency on Jetson vLLM servers by appending speculative decoding configuration, with guidance on when to enable and how to benchmark the improvement.

Recommends an inference runtime and memory-related launch flags for LLM/VLM workloads on NVIDIA Jetson devices, based on a live memory audit snapshot.

Inspects a Jetson Linux_for_Tegra BSP tree on the host PC and prints a concise summary including L4T version, board configs, and rootfs state.

Lint and format Python code for Megatron-LM using ruff, black, isort, pylint, and mypy, with commands for autoformatting and import ordering.

Captures a baseline snapshot of a Jetson device's module model, L4T version, kernel, OS version, and power mode for performance testing or verification.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Query experiments, protocols, resources, and inventory in the Labstep electronic lab notebook using the labstepPy API.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies for maximum GPU efficiency.

Queries and displays Labstep electronic lab notebook data — experiments, protocols, resources, and inventory — via labstepPy, with an offline demo mode using synthetic biology data.

Augments nearest-neighbour search with graph Laplacian features to retrieve items based on both semantic similarity and structural role.

Simulates meiotic recombination to produce offspring genomes from parent pairs, modeling Mendelian segregation, de novo mutation, sex determination, trait inference, and clinical evaluation against a disease registry.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques for 1.5-3.6× speedup without quality loss.

Benchmark, load test, capacity plan, and cache with k6, JMeter, Locust, and pgbench. Use when the user says "slow", "performance", "load test", "stress test", "how many users can it handle", "capacity", "cache", "benchmark", "k6".

Mine, stake, and manage LITCOIN tokens on Base blockchain using the Python SDK, with options for comprehension mining or LLM-powered research mining.

Install a local rebuttal workspace for academic papers with structured intake, reviewer analysis, and strategy planning to produce venue-compliant author responses.

Ableton Live Object Model (LOM) API reference for Python Remote Scripts and control surface development.

Bedside prescribing reference for Bemdec (bempedoic acid / NEXLETOL) — indication check, dose, statin co-prescribing safety caps, monitoring plan, warnings for hyperuricemia and tendon rupture, and special population guidance. Use when a clinician asks "can I start bempedoic acid", "Bemdec indication", "is bempedoic acid safe with my statin", "patient on Nexletol has joint pain or high uric acid", "bempedoic acid in CKD or liver disease or pregnancy", or any prescribing or monitoring question about bempedoic acid.

Train reinforcement learning agents at millions of steps per second using optimized PPO, vectorized environments, and multi-agent support.

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

Universal transformation λ(ο,K).τ with recursive self-improvement. USE WHEN routing reasoning, validating knowledge graphs, preparing CICM/ANZCA examinations, or when self-improvement of reasoning/architecture/context is required. Routes queries through R0-R3 complexity pipelines, validates topology (η≥target) and governance (KROG), emits per style (Φ), and compounds learnings into knowledge K. Triggers on complexity assessment, multi-step reasoning, examination mode, or /λ invocation.

Local RAG indexing with 97% storage reduction via anchor-based lazy recomputation. Graph-based selective embedding storage for memory-efficient semantic code search.

Build streaming data pipelines with Redpanda Connect using declarative YAML configs, Bloblang mappings, and component discovery. Covers running, linting, and dry-running pipelines.

Process and analyze mass spectrometry data with the Matchms Python library, including importing spectra, filtering peaks, calculating similarity scores, and building reproducible analytical workflows.

LEMON v2.0 — The Degen Fader. Identifies historically reckless traders (DEGEN activity + CHOPPY consistency) on Hyperliquid, monitors their live positions, and counter-trades them when they're bleeding at high leverage. If a cluster of degens goes max-leverage long on a coin and starts losing, LEMON shorts it — betting on their inevitable liquidation cascade. DSL exit managed by plugin runtime via runtime.yaml.

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

Evaluates likelihood of primary aldosteronism by measuring plasma aldosterone suppression after oral captopril; normal suppression ≥30% makes PA unlikely, while lack of suppression with persistently suppressed plasma renin activity suggests PA. Use when assessing captopril challenge test (CCT) results for PA diagnosis in patients with positive aldosterone-to-renin ratio.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

Recursive self-improving holon λ(ο,Κ,Σ).τ' for knowledge compounding and schema evolution. USE WHEN learning, improving, optimizing, assessing, reflecting, debugging, synthesizing, or refining—whether human, AI, or organizational. Triggers on /learn, /compound, /improve, /refine, /optimize, /assess, /reflect, "lessons learned", "best practices", "continuous improvement". Preserves Κ-monotonicity, η≥4, homoiconicity.