director-ai Files

Real-time LLM hallucination guardrail — NLI + RAG fact-checking

Brought to you by: anulum

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
README.md	2026-03-01	754 Bytes	0
v1.4.1 -- ORT optimization + ONNX GPU benchmarks source code.tar.gz	2026-03-01	1.4 MB	0
v1.4.1 -- ORT optimization + ONNX GPU benchmarks source code.zip	2026-03-01	1.5 MB	0
Totals: 3 Items		2.9 MB	0

Changes

ORT_ENABLE_ALL graph optimization on ONNX inference sessions
Suppress Memcpy transformer warnings (log_severity_level=3)
MiniCheck AggreFact benchmark (benchmarks/aggrefact_minicheck.py)
ONNX GPU batch benchmarks: 14.6 ms/pair (DeBERTa-v3-Large, GTX 1060)
Zenodo DOI: 10.5281/zenodo.18822167
Version bump to 1.4.1

Performance (FactCG-DeBERTa-v3-Large)

Backend	Latency (ms/pair)
PyTorch GPU batch	19.0
ONNX GPU batch	14.6
Production NLIScorer	13.2
Raw ORT (short inputs)	9.0
Heuristic (no model)	0.03

Accuracy

75.8% balanced accuracy on LLM-AggreFact (29K samples, 4th on leaderboard)

Source: README.md, updated 2026-03-01

Other Useful Business Software

Try Google Cloud Risk-Free With $300 in Credit Icon

Try Google Cloud Risk-Free With $300 in Credit

No hidden charges. No surprise bills. Cancel anytime.

Use your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.

Start Free

MongoDB Atlas runs apps anywhere Icon

MongoDB Atlas runs apps anywhere

Deploy in 115+ regions with the modern database for every enterprise.

MongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.

Start Free

Try Google Cloud Risk-Free With $300 in Credit

No hidden charges. No surprise bills. Cancel anytime.

Use your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.

Start Free

Recommended Projects

Opik
Debug, evaluate, and monitor your LLMapps, RAG systems, and agentic AI
DocsGPT
Private AI platform for agents, enterprise search and RAG pipelines
DeepEval
DeepEval is a simple-to-use, open-source LLM evaluation framework, for evaluating and testing large-language model systems. It is similar to Pytest but specialized for unit testing LLM outputs. DeepEval incorporates the latest research to evaluate LLM outputs based on metrics such as G-Eval, hallucination, answer relevancy, RAGAS, etc., which uses LLMs and various other NLP models that run locally on your machine for evaluation. Whether your application is implemented via RAG or fine-tuning, LangChain, or LlamaIndex, DeepEval has you covered. With it, you can easily determine the optimal hyperparameters to improve your RAG pipeline, prevent prompt drifting, or even transition from OpenAI to hosting your own Llama2 with confidence.
Haystack
Haystack is an open source NLP framework to interact with your data
tactile12000 mp3 dj ware
The Tactile12000 is a visual DJ setup for MP3 files on your Mac or PC. It's built using Macromedia Director and a plug-in written in C++. Visit www.tactile12000.com for more information.