Results for “hla-typing”

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

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

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.

Search the Hugging Face Hub for llama.cpp-compatible GGUF models, select the right quantization, and run them locally with llama-cli or llama-server.

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.

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.

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.

Holarchic reasoning framework implementing λ-calculus over simplicial complexes. Entities (ο) transform through operations (λ) toward terminals (τ) via the universal form λο.τ. Persistent homology captures multi-scale structure; sheaf theory ensures local-to-global consistency. Use when knowledge requires: (1) homoiconic self-reference where structure mirrors content, (2) scale-invariant holonic decomposition, (3) topological invariants preserved across transformations, or (4) formal Lex-style axiom systems over property graphs.

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

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.

Run LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Design lean startup experiments (pretotypes) for a new product by creating XYZ hypotheses and suggesting low-effort validation methods like landing pages, explainer videos, and pre-orders.

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

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.

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

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.

Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.

Imported skill tracing from langchain

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Designs Elasticsearch indexes and mappings, tunes queries, sizes clusters, and handles operations like shard/replica strategy, ILM, monitoring, troubleshooting, and safe reindexing or upgrades.

Stand up a self-hostable, typo-tolerant search environment with Typesense — the open-source Algolia / ElasticSearch alternative (single C++ binary, <50ms instant search, no runtime deps). One routing-first skill: pick a server mode (binary download, official Docker image, or managed Typesense Cloud), install an API client (Python/JS/PHP/Ruby official; Go/Dart/C# community), design a collection schema, index documents, and run searches with typo tolerance, faceting/filtering, geo-search, sorting, grouping, synonyms, curation, scoped API keys, and federated multi-search — then wire an InstantSearch.js UI and a Raft-based HA cluster for production. Use when the user wants to build or operate an installable search backend, add site/app/product search, or migrate off Algolia/Elasticsearch. Triggers on: typesense, search engine, typo-tolerant search, algolia alternative, elasticsearch alternative, instantsearch, faceted search, geo search, vector search, self-hosted search, site search, product search.

Enables visual instruction tuning and image-based conversations using open-source vision-language models. Supports multi-turn image chat, visual question answering, and image understanding tasks.

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

Answer detailed or normative questions about Python's type system using the complete vendored typing specification. Use for subtle assignability, generics, variance, protocols, overloads, narrowing, qualifiers, TypedDict, or checker-semantics questions that exceed everyday annotation guidance.

Classifies HTML pages, forms, and fields using machine learning to detect page types, form types, and field types from HTML content or URLs.

Proposal research workflow that matches local case studies and gathers web evidence into an HTML research dossier. Use when the user needs proposal research, client intel, tech stack discovery, pricing benchmarks, competitive context, or case-study matching for a brief. Triggers: 'research this proposal', 'build a research dossier', 'match case studies', 'find pricing benchmarks', 'client intel for', 'what tech does X use'.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag) using standardized prompts and metrics. Supports HuggingFace, vLLM, and API backends.

Convert and quantize models to GGUF format for efficient CPU/GPU inference with llama.cpp, supporting 2-8 bit quantization and Apple Silicon acceleration.

Builds NLP pipelines with Haystack for document search, QA, and LLM-powered applications.

Use when implementing haskell functionality with production-grade patterns and safeguards.

Build industrial-grade SCADA/HMI dashboards in MATLAB following industrial-HMI conventions (ISA-101-aligned): gray-field philosophy, alarms at source, write safeguards, fixed-range trends, drill-down layout. Produces a real App Designer app (.mlapp, or plain-text .m+.xml on R2026b+) by handing serialization to the matlab-build-app skill when available, and falls back to a programmatic .m app otherwise. Use when wrapping OPC UA / Modbus / MQTT / OSI PI / PI AF monitoring scripts into a live operator app, building plant overviews, designing operator dashboards, or any time a user asks for a "SCADA dashboard", "HMI", "plant dashboard", "operator screen", or "industrial monitoring app" in MATLAB. Trigger on: SCADA, HMI, industrial dashboard, plant overview, operator screen, uigauge, uilamp, alarm banner, gray-field, ISA-101, OPC UA dashboard, setpoint, write safeguards, alarm visualization, OSIsoft PI, AVEVA PI, PI Server, PI Data Archive, PI AF, PI Asset Framework, piclient, afclient.

Hedging Expert Advisor in Python with trailing stop and automated pending orders, converted from MQL5 and cross-platform compatible with mt5linux Docker.

Run GGUF models locally with llama.cpp, including finding the right file on the Hugging Face Hub, installing, quantizing, serving, and using Python bindings.

---