Tag

Outlines

Ensures LLM outputs match precise, schema-defined structures by enforcing Python types, Pydantic models, JSON schemas or grammars at generation time. Provider-agnostic integrations (OpenAI, transformers, vLLM, Ollama, etc.) and function-call style mapping reduce brittle post-processing and make structured generation reliable for production pipelines.

databricks-dolly-15k

A 15,000+ English instruction–response corpus for fine-tuning and evaluating LLM instruction-following behavior. Contains human-authored prompts and answers across categories (closed/open QA, summarization, extraction, classification, brainstorming) and is released under CC BY-SA 3.0.

Hermes Function-Calling V1

Structured dataset for training and evaluating LLM agentic behavior: function-calling conversations, JSON-mode structured outputs, and extraction samples for teaching models to generate tool calls and strict structured responses. Includes single-turn and multi-turn scenarios across several configs.

Model Context Protocol

An open protocol that standardizes how LLM applications connect to external data sources, tools, and services via JSON-RPC — TypeScript-first schema with JSON Schema exports, SDKs, and centralized documentation to enable interoperable integrations.

Enforces output grammars during LLM decoding while reducing CPU validation overhead. Precomputed token masks and persistent stacks support nested formats without checking the full vocabulary at every step.

AI Coding Assistant Training Data Extraction Toolkit

Extracts local chat logs, code context, diffs, and tool outputs from AI coding assistants and exports them as ML-ready JSONL. Auto-discovers common storage locations and handles SQLite/JSONL formats; scan extracted files for secrets before sharing.

Apache Ossie

Defines a vendor-neutral JSON/YAML semantic model specification and tooling to exchange metrics, dimensions, lineage and other business semantics across analytics, AI and BI platforms; includes a core spec, validators, converters (dbt, GoodData, Salesforce) and example models.

Headroom

Compresses tool outputs, logs, files and RAG chunks locally before they reach the LLM to reduce token usage while caching originals for on-demand retrieval. Provides proxy/library/wrap modes, JSON- and code-aware compressors, and reversible compression.

Hyper-Extract

Transforms unstructured documents into strongly-typed Knowledge Abstracts with one CLI command, extracting entities and relations into graphs, hypergraphs, and spatio‑temporal structures. Includes 80+ templates, multiple RAG engines, local vLLM support, Obsidian export and an MCP server.

UnsolvedMath

Provides a machine-readable collection of 5,426 open and historically significant mathematical problems with LaTeX statements, structured metadata and curated per-problem AI-assisted research notes. Includes difficulty labels, canonical problem sets (Millennium, Hilbert, Erdős) and files optimized for benchmarking math reasoning.

OfficeCLI

Provides a command-line interface for AI agents to create, read, render, and modify Word/Excel/PowerPoint files headlessly. Includes a built-in high-fidelity HTML/PNG renderer, deterministic JSON APIs, resident mode and an MCP server for direct agent integration—suited for CI, containers, and automated document pipelines.

Türkçe Atlas — Instruct SFT

Provides 336,146 Turkish instruction-following chat examples (system→user→assistant) for supervised fine-tuning; single train split (no validation/test), reported MIT license, diverse tasks (rewrites, summarization, QA) and a uniform system prompt that may bias model behavior.