Tag
Explore by tags
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.
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.
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.
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.
Provides 40 public Kubernetes incident scenarios (SRE subset) with ground-truth root-cause entities and offline cluster snapshots in JSONL format; designed to evaluate agentic root-cause diagnosis on alerts, events, traces and topology.
Provides the gated, official OSWorld 2.0 Python task class files (task_*.py) required to run the benchmark; distributed via a Hugging Face gated dataset to reduce benchmark leakage. Download requires accepting gated access on Hugging Face.
Provides kanji-level evaluation data for Japanese TTS: disambiguated sentence contexts targeting 4,378 kanji-reading pairs (2,136 Jōyō kanji) with 13,095 native-speaker–verified sentences and katakana-marked ground-truth readings for kanji-level error metrics.
Curates ~1.1M instruction–response examples for 'vibe coding' scenarios where developers prompt LLMs to produce implementation plans, architecture choices, and deployment steps. Covers conversation memory, prompt templates, model routing, streaming responses, and scaling considerations; Apache-2.0.
Contains 603 coding and math prompt–response pairs produced by Claude Fable‑5 (generated 2026-06-10), provided as a JSONL subset for fine-tuning, evaluation, and behavior analysis. Responses are 'non-thinking' (no chain-of-thought); small, anonymized, and lacking an explicit license.
Provides a deduplicated 2.0M-row corpus of FABLE.5 / Mythos agent traces with row-level provenance and session-limit rows removed. Includes canonical Parquet and gzip JSONL exports, SHA256 row hashes, and provenance fields for tracing first-source datasets.
Provides 319 newline-delimited JSON agent session traces captured from GLM-5.2 using Teich for training agentic models. Preserves reasoning-first assistant fragments, tool-call events, and a dataset-level training-ready tool schema; convertible to OpenAI-style JSONL for SFT/distillation.
Provides 2,170 reference-grounded evaluation samples across seven agent domains (MCP, Search, Terminal, SWE, Android, Web, OS) to score language world models on Format, Factuality, Consistency, Realism and Quality. Includes per-domain JSONL files, judge prompts and an evaluation script for reproducible scoring.