"leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents".
Directory
Search results
Published directory entries matching your search.
Vega is an AutoML algorithm tool chain developed by Noah's Ark Laboratory. It covers hyperparameter optimization, data augmentation, network architecture search, model compression and fully train functions, and supports PyTorch, TensorFlow and MindSpore backends.
VerbForm is a GitHub repository or organization with source code, releases, documentation, or project resources.
VeritasGraph is an open-source knowledge graph and GraphRAG framework. It supports multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over user data, using nodes, edges, RDF, and linked data. The project runs locally or in the cloud.
VideOCR is a tool that extracts hardcoded subtitles from video files using a simple graphical user interface and machine learning technology. It supports more than 200 languages, and its source code is hosted on GitHub.
Videos is a GitHub repository or organization with source code, releases, documentation, or project resources.
Vim University is a GitHub repository or organization with source code, releases, documentation, or project resources.
Some of the python libraries were cut-and-pasted from.
OpenClaw AI agent skill for automated TikTok and Instagram carousel growth. Pass any website URL to analyze brand, competitors, colors, value proposition. Generates 6 visually coherent slides and auto-publishes with trending music via upload-post API. Built-in analytics and learning loop. Free tier, no credit card. Larry alternative.
Virgilio is a GitHub repository or organization with source code, releases, documentation, or project resources.
Machine Learning Operations - An awesome list of references for MLOps.
A comprehensive testing and evaluation framework for voice agents across language models, prompts, and agent personas.
Cloud Native Batch System (Project under CNCF).
Wasona is a GitHub repository or organization with source code, releases, documentation, or project resources.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
Webb Compare is a GitHub repository or organization with source code, releases, documentation, or project resources.
Webrtc For The Curious is a GitHub repository or organization with source code, releases, documentation, or project resources.
WFGY is an open-source project focused on AI reasoning, retrieval-augmented generation, AI agents, and real-world workflows. It is developing the WFGY 5.0 Polaris Protocol, and currently includes components such as the Problem Map, Global Debug Card, 4.0 version, and CFV Easter Egg.
Whylogs is an open-source data logging library for machine learning models and data pipelines. It provides visibility into data quality and model performance over time, and supports privacy-preserving data collection to support system safety and robustness.
wik is a command-line tool that retrieves information from Wikipedia directly in the terminal. It allows users to search for Wikipedia articles, retrieve summaries of topics, view full article information, select the language for content, access random Wikipedia articles, and caches retrieved pages on disk for faster repeated access and offline use.
Wiki is a Linux or Unix documentation project with guides, references, or manuals.
An implementation of Dell Zhang's solution to Wikipedia's Participation Challenge on Kaggle.
Wikiman is a universal offline documentation search engine for manual pages, tldr-pages, ArchWiki, Gentoo Wiki, DevDocs, and FreeBSD documentation. It offers browsing without needing exact terms or an internet connection by using full-text search for wikis, partial name and description matching for man pages, and fuzzy filtering for search results.
WizardLM is a repository of large language models including WizardLM, WizardCoder and WizardMath, described as LLMs built upon Evol Instruct. The page lists model checkpoints and benchmark results, with WizardCoder-33B-V1.1 reported at 79.9 pass@1 on HumanEval and WizardMath-7B-V1.1 reported at 83.2 pass@1 on GSM8k.