K

.md Directory

All Documents New Popular

K

All Documents — .md Directory | Neura Market

All Documents

3,528 documents available

BENCHMARKS.md

PkVision — Roadmap

- [ ] **Docker + docker-compose** — Containerize the full stack (API + worker + Redis + PostgreSQL). Single `docker-compose up` to run everything. GPU passthrough support for training with NVIDIA Container Toolkit. Separate `Dockerfile.api` (lightweight, inference only) and `Dockerfile.train` (full ML deps + CUDA/MPS).

aiworkflow

AirKyzzZ

BENCHMARKS.md

OABench: Benchmarking Large Language Models on the Brazilian Bar Examination

**Roberto T. Cestari**

aillmeval

robertotcestari

BENCHMARKS.md

Development notes

- Replicated benchmark LigthGBM classifier model

anweshatd

BENCHMARKS.md

What If You Could Run 20 AI Agents in One Terminal?

I didn't plan to build a parallel agent runtime. I was exploring what CLI coding agents could do, and one experiment kept leading to the next.

aiagentprompt

DUBSOpenHub

BENCHMARKS.md

Useful Data Sources

Everyone enjoys discovering [interesting datasets](http://rs.io/100-interesting-data-sets-for-statistics/), but useful datasets are even better. The problem is that the open data movement has been too successful by some measures.

aieval

DS4PS

BENCHMARKS.md

TerrainGossip: Decentralized Infrastructure for AI Manipulation Detection

> A gossip-based protocol for distributed LLM evaluation, behavioral monitoring, and evidence collection—built to resist manipulation of the monitoring system itself.

aillmrag

rng-ops

BENCHMARKS.md

How to use the AI Technology Radar

**The Radar around the Development of professional AI Agents, RAG Systems and LLMOps.**

aiagentllm

AOEpeople

CLAUDE.md

Giva - Generative Intelligent Virtual Assistant

A macOS-native personal assistant that syncs emails and calendar from Apple Mail/Calendar,

aiagentllm

Cognivix

SPEC.md

SPEC: HackTheBench Agent Support

> AI agents (Claude Code, Codex, Gemini CLI) compete on the same CTF benchmark as humans, with verified badges on the leaderboard.

aiagentmcp

The-Bench-Co

BENCHMARKS.md

WARP.md

This file provides guidance to WARP (warp.dev) when working with code in this repository.

airageval

MylesLandais

BENCHMARKS.md

Summary

title: 'CAWSR: Carla-AutoWare Scenario Runner'

aiagenteval

Intelligent-Testing-Lab

CLAUDE.md

This file provides guidance to Claude Code when working with this repository.

aillmeval

bdschi1

BENCHMARKS.md

PHM-LLM Template Setup Guide

This guide will help you quickly set up and customize the PHM-LLM template for your prognostic health management project.

aiagentllm

liq22

BENCHMARKS.md

Trust: A Multi-Level Exploration and Framework

Below are five distinct ways to define **Trust**, arranged in increasing depth and complexity (without explicit grade-level labels, yet offering progressive sophistication “HBS style”).

aiagent

adnanmasood

BENCHMARKS.md

Prometheus Automation AI Marketplace - Project Documentation

**Project Name**: Prometheus Store

aiworkflowautomation

Prometheus-Automation

replit.md

Overview

Compare Models is a daily-updated leaderboard system that aggregates LLM performance data from the Chatbot Arena with pricing information from multiple sources. The application automatically scrapes model rankings from OpenLM.ai's Chatbot Arena+ leaderboard, fetches pricing data from OpenRouter and LiteLLM, and produces a unified CSV dataset. It includes a web interface for searching models, calculating costs, and comparing quality-to-price ratios. The system runs automated daily updates via Git

aillmrag

ZachLaik

BENCHMARKS.md

Large Language Models — Structured Notes

- A mathematical function that takes text as input and returns a probability distribution over possible next tokens

aillmrag

SqrtNegativOne

BENCHMARKS.md

Benchmarks

Benchmarks have been implemented with [BenchmarkDotNet](https://github.com/PerfDotNet/BenchmarkDotNet).

MichaCo

BENCHMARKS.md

Benchmarks

This project uses [Criterion](https://github.com/bheisler/criterion.rs) for benchmarking.

mpiton

BENCHMARKS.md

Pasto Performance Benchmarks

This document contains performance benchmarks for Pasto across different hardware configurations.

ralsina

BENCHMARKS.md

Konverter Benchmarks

Comparison of a model converted with SNPE 1.19 (Snapdragon Neural Processing Engine) and the same model converted with Konverter.

rag

sshane

BENCHMARKS.md

BENCHMARKS

The math in gf256 is very close to the hardware, and for each algorithm, there

geky

BENCHMARKS.md

Benchmarks

Since Okra is built on top of LMDB and exposes the same external key/value store interface, we can compare Okra's performance to using LMDB directly. The numbers here were produced on a 2021 M1 MacBook Pro with 32GB RAM running macos 13.1 with a 1TB SSD.

canvasxyz

EVALS.md

soumith.convnet-benchmarks

Easy benchmarking of all public open-source implementations of convnets.

airag

DLR-SC

Page 81 of 147

All Documents

PkVision — Roadmap

OABench: Benchmarking Large Language Models on the Brazilian Bar Examination

Development notes

What If You Could Run 20 AI Agents in One Terminal?

Useful Data Sources

TerrainGossip: Decentralized Infrastructure for AI Manipulation Detection

How to use the AI Technology Radar

Giva - Generative Intelligent Virtual Assistant

SPEC: HackTheBench Agent Support

WARP.md

Summary

CLAUDE.md

PHM-LLM Template Setup Guide

**Trust: A Multi-Level Exploration and Framework**

Prometheus Automation AI Marketplace - Project Documentation

Overview

Large Language Models — Structured Notes

Benchmarks

Benchmarks

Pasto Performance Benchmarks

Konverter Benchmarks

BENCHMARKS

Benchmarks

soumith.convnet-benchmarks

Trust: A Multi-Level Exploration and Framework