Skill UI

Chroma is an open-source, AI-native embedding database designed for building sophisticated LLM applications. It allows users to store high-dimensional embeddings and associated metadata, facilitating powerful vector search and full-text filtering. Ideal for implementing Retrieval-Augmented Generation (RAG) systems, semantic search, and document retrieval in local or self-hosted environments, making it perfect for open-source AI projects and prototyping.

llama.cpp is a pure C/C++ library designed for efficient LLM inference, optimized to run on resource-constrained environments. It excels in scenarios where high-end NVIDIA GPUs (CUDA) are unavailable, making it ideal for Apple Silicon Macs, AMD/Intel GPUs, or edge deployment devices like Raspberry Pi. It supports GGUF quantization formats, enabling significant memory reduction and speed improvements for local, cross-platform AI applications.

Outlines guarantees valid JSON/XML/code outputs by applying CFG/FSM-constrained token filtering, Pydantic schemas, and grammar-level sampling while supporting local Transformers, llama.cpp, and vLLM backends for fast inference.

A comprehensive skill for fine-tuning and training large language and vision models using advanced techniques like TRL (SFT, DPO, GRPO) or Unsloth. This process runs entirely on managed Hugging Face cloud GPUs, eliminating the need for local GPU setup. It supports modern training workflows, model conversion (GGUF for local deployment), and ensures seamless artifact storage to the Hugging Face Hub.

An expert guide for deploying and optimizing Large Language Models (LLMs) entirely on local hardware. Mastering the entire local AI ecosystem, including inference engines like Ollama, vLLM, and llama.cpp. Provides deep knowledge on quantization formats (GGUF, EXL2, AWQ), VRAM calculation, and ensuring privacy-first, offline deployment for state-of-the-art models.

This skill is designed for running comprehensive evaluations of Hugging Face Hub models on local hardware. It supports multiple evaluation frameworks, including `inspect-ai` and `lighteval`, and provides flexibility in backend selection (e.g., `vllm`, Transformers, or `accelerate`) to optimize for performance and compatibility. Use this for local GPU benchmarking, smoke testing, and backend selection, but note that it does not handle remote job orchestration or result publishing.

Plans, audits, and safely runs ChicagoHAI HypoGeniC/HypoRefine workflows for LLM-assisted hypothesis generation from labeled text datasets, with pinned installs, config validation, dataset leakage checks, and bounded local review before any model call.

This skill provides advanced sentiment analysis tailored for financial news and market texts. It supports two modes: high-speed, localized analysis using FinBERT, and advanced, reasoning-based analysis via LLM. Users can determine the sentiment polarity (positive, negative, or neutral), score, and specific reason for financial content, making it ideal for market intelligence and data enrichment.

A comprehensive guide to using AssemblyAI for rich audio processing. This guide covers basic speech-to-text transcription from URLs or local files, along with advanced AI features. Capabilities include speaker diarization, sentiment analysis, key phrase extraction, entity detection, and powerful LLM-powered analysis (LeMUR) for summarization and Q&A. Ideal for integrating deep, multi-faceted audio insights into applications.

A comprehensive guide and skill for deploying large language models (LLMs) locally using the llama.cpp framework and GGUF quantization format. It covers searching the Hugging Face Hub, selecting optimal quantizations (e.g., Q4_K_M), running local servers, and achieving OpenAI-compatible API endpoints. Supports various hardware backends including CPU, Mac Metal, CUDA, and ROCm. Ideal for developers needing offline, private LLM inference.

Format chat messages into local model templates (llama3, mistral, chatml, phi, gemma, or a model id) and route queries through a small WASM HNSW pattern index. Useful for preparing prompts for llama.cpp, Ollama, and other local runtimes.

Provides comprehensive configuration management for local LLM inference using RuVLLM. Users can select models, perform task-specific fine-tuning with MicroLoRA adapters, or implement continuous, real-time adaptation using SONA. This tool guides the entire advanced LLM workflow, covering status checks, configuration generation, and advanced adaptation loops.