Search Results for "benchmarks" - Page 10
Sort By:
Showing 440 open source projects for "benchmarks"
View related business solutions-
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
1
Prisme Analytics
An Open Source, privacy-focused and progressive analytics service.
... * Lightweight: Prisme tracking script is less than 1kB (~45x smaller than Google Analytics). * Resource efficient: Prisme is designed to be fast and resource efficient, checkout our benchmarks. SPA support: Prisme is built with modern web frameworks in mind and it works automatically with any pushState based router on the frontend. * Grafana based: Prisme integrates with Grafana that provides: * User managements * Team management -
2
DeepSeek MoE
Towards Ultimate Expert Specialization in Mixture-of-Experts Language
...For example, their MoE variant with 16.4B parameters claims comparable or better performance to standard dense models like DeepSeek 7B or LLaMA2 7B using about 40% of the total compute. The repo publishes both Base and Chat variants of the 16B MoE model (deepseek-moe-16b) and provides evaluation results across benchmarks. It also includes a quick start with inference instructions (using Hugging Face Transformers) and guidance on fine-tuning (DeepSpeed, hyperparameters, quantization). The licensing is MIT for code, with a “Model License” applied to the models. -
3
FrenchKiss.js
The blazing fast lightweight internationalization (i18n) module
...FrenchKiss is by now, the fastest i18n JS package out there, working 5 to 1000 times faster than any others by JIT compiling the translations, try it by running the benchmarks. -
4
DB-GPT-Hub
A repository that contains models, datasets, and fine-tuning
...The repository includes datasets and experiment configurations that allow researchers to train models on real database schemas and evaluate them using standardized benchmarks. Its design encourages experimentation with different large language models and fine-tuning techniques, including parameter-efficient training approaches. -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
5
YiVal
Your Automatic Prompt Engineering Assistant for GenAI Applications
...YiVal supports integration with various LLM providers and can orchestrate experiments across different models, making it adaptable to evolving AI ecosystems. It also includes evaluation pipelines that help quantify output quality based on criteria such as accuracy, coherence, or task-specific benchmarks. -
6
State of Open Source AI
Clarity in the current fast-paced mess of Open Source innovation
...Because the AI domain moves quickly, part of the aim is to make the content maintainable and updateable by the community. The structure includes chapters or sections about model formats, evaluation benchmarks, hardware/backends, MLOps systems, alignment and safety issues, and open datasets. The repository contains the text (in Markdown or similar), configuration for build or publishing (static site or e-book), and contributor guidelines. -
7
Demucs
Code for the paper Hybrid Spectrogram and Waveform Source Separation
...The repository includes pretrained models for common tasks such as isolating vocals, drums, bass, and accompaniment from stereo music, achieving state-of-the-art results in benchmarks like MUSDB18. Demucs supports GPU-accelerated inference and can process multi-channel audio with chunked streaming for real-time or batch operation. It also provides training scripts and utilities to fine-tune on custom datasets, along with remixing and enhancement tools. -
8
Detectron
FAIR's research platform for object detection research
Detectron is an object detection and instance segmentation research framework that popularized many modern detection models in a single, reproducible codebase. Built on Caffe2 with custom CUDA/C++ operators, it provided reference implementations for models like Faster R-CNN, Mask R-CNN, RetinaNet, and Feature Pyramid Networks. The framework emphasized a clean configuration system, strong baselines, and a “model zoo” so researchers could compare results under consistent settings. It includes... -
9
GLM-130B
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
...It is designed for large-scale inference and supports both left-to-right generation and blank filling, making it versatile across NLP tasks. Trained on over 400 billion tokens (200B English, 200B Chinese), it achieves performance surpassing GPT-3 175B, OPT-175B, and BLOOM-176B on multiple benchmarks, while also showing significant improvements on Chinese datasets compared to other large models. The model supports efficient inference via INT8 and INT4 quantization, reducing hardware requirements from 8× A100 GPUs to as little as a single server with 4× RTX 3090s. Built on the SwissArmyTransformer (SAT) framework and compatible with DeepSpeed and FasterTransformer, it supports high-speed inference (up to 2.5× faster) and reproducible evaluation across 30+ benchmark tasks. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
10
MetaTransformer
Meta-Transformer for Unified Multimodal Learning
We're thrilled to present OneLLM, an ensembling Meta-Transformer framework with Multimodal Large Language Models, which performs multimodal joint training, supports more modalities including fMRI, Depth, and Normal Maps, and demonstrates very impressive performances on 25 benchmarks. -
11
ReAct Prompting
Synergizing Reasoning and Acting in Language Models
...This alternating sequence of reasoning, acting, and observing results allows the model to gather additional information and refine its decision-making process during task execution. The framework has been tested on several benchmarks including question answering, fact verification, and interactive decision-making tasks, demonstrating improved performance compared to methods that rely only on reasoning. -
12
learn2learn
A PyTorch Library for Meta-learning Research
Learn2Learn is a PyTorch-based library focused on meta-learning and few-shot learning research. It provides reusable components and meta-learning algorithms, making it easier to build, train, and evaluate models that can quickly adapt to new tasks with minimal data. Learn2Learn is widely used in research for tasks such as few-shot classification, reinforcement learning, and optimization. -
13
fastMRI
A large open dataset + tools to speed up MRI scans using ML
fastMRI is a large-scale collaborative research project by Facebook AI Research (FAIR) and NYU Langone Health that explores how deep learning can accelerate magnetic resonance imaging (MRI) acquisition without compromising image quality. By enabling reconstruction of high-fidelity MR images from significantly fewer measurements, fastMRI aims to make MRI scanning faster, cheaper, and more accessible in clinical settings. The repository provides an open-source PyTorch framework with data... -
14
AB3DMOT
Official Python Implementation for "3D Multi-Object Tracking
...This relatively simple design allows the tracker to achieve very high processing speeds while maintaining competitive tracking accuracy. The project also introduces new evaluation metrics specifically designed for assessing performance in 3D tracking benchmarks. The framework has been evaluated on widely used datasets such as KITTI and nuScenes and demonstrates strong performance compared with more complex tracking systems. -
15
DiT (Diffusion Transformers)
Official PyTorch Implementation of "Scalable Diffusion Models"
...The model architecture parallels large language models but for image tokens—each block refines noisy latent representations toward cleaner outputs through iterative denoising steps. DiT achieves strong results on benchmarks like ImageNet and LSUN while being architecturally simple and highly modular. It supports variable resolution, conditioning on class or text embeddings, and integration with latent autoencoders (like those used in Stable Diffusion). -
16
Hyperformer
Hypergraph Transformer for Skeleton-based Action Recognition
This is the official implementation of our paper "Hypergraph Transformer for Skeleton-based Action Recognition." Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections. By defining a graph with joints as vertices and their natural connections as edges, previous works successfully adopted Graph Convolutional networks (GCNs) to model joint co-occurrences and achieved superior performance. More recently, a limitation of... -
17
-
18
FFCV
Fast Forward Computer Vision (and other ML workloads!)
ffcv is a drop-in data loading system that dramatically increases data throughput in model training. From gridding to benchmarking to fast research iteration, there are many reasons to want faster model training. Below we present premade codebases for training on ImageNet and CIFAR, including both (a) extensible codebases and (b) numerous premade training configurations. -
19
FuzzBench
FuzzBench - Fuzzer benchmarking as a service
FuzzBench is a large-scale, open research platform developed by Google to evaluate and benchmark fuzzers — automated software testing tools that detect vulnerabilities through randomized input generation. It provides a standardized, reproducible environment for comparing the performance and effectiveness of different fuzzing algorithms on real-world software targets. FuzzBench integrates with the OSS-Fuzz infrastructure, allowing it to run experiments on authentic open source projects and... -
20
ConvNeXt V2
Code release for ConvNeXt V2 model
...A key innovation is a new Global Response Normalization (GRN) layer added to the ConvNeXt backbone, which enhances feature competition across channels. The result is a convnet that competes strongly with transformer architectures on recognition benchmarks while being efficient and hardware-friendly. The repository provides official PyTorch implementations for multiple model sizes (Atto, Femto, Pico, up through Huge), conversion from JAX weights, code for pretraining/fine-tuning, and pretrained checkpoints. It supports both self-supervised pretraining and supervised fine-tuning. -
21
ixy-languages
A high-speed network driver written in C, Rust, C++, Go, C#, Java
...The repository helps systems and networking learners understand how low-level I/O code behaves differently in memory-safe languages versus unsafe ones. Each language subdirectory includes build scripts, language-specific idioms (e.g. unsafe blocks in Rust), binding layers, and benchmarks for packet I/O and latency. -
22
Finatra
Fast, testable, Scala services built on TwitterServer and Finagle
Finatra builds on TwitterServer and uses Finagle, therefore it is highly recommended that you familiarize yourself with those frameworks before getting started. The version of Finatra documented here is version 2.x. Version 2.x is a complete rewrite over v1.x and as such many things are different. Finatra at its core is agnostic to the type of service or application being created. It can be used to build anything based on TwitterUtil: c.t.app.App. For servers, Finatra builds on top of the... -
23
albert_zh
Implementation of A Lite Bert For Self-Supervised Learning Language
...The project includes several model variants, such as tiny, small, base, large, and xlarge-style releases, giving users options for speed, size, and accuracy tradeoffs. It also provides guidance for fine-tuning downstream tasks such as sentence-pair semantic similarity and Chinese classification benchmarks. The repository includes support paths for TensorFlow, PyTorch conversion, Keras loading, TensorFlow 2.0 loading, and TensorFlow Lite deployment for mobile scenarios. Overall, it is useful for Chinese NLP developers who need compact pretrained language models for classification, similarity, and other language understanding tasks. -
24
DialoGPT
Large-scale pretraining for dialogue
...DialoGPT provides multiple pretrained model sizes and includes code for training, fine-tuning, and evaluating dialogue generation models. The repository also contains scripts for preparing conversation datasets and reproducing experimental benchmarks related to conversational AI research. -
25
Jason
A blazing fast JSON parser and generator in pure Elixir
A blazing-fast JSON parser and generator in pure Elixir. The parser and generator are at least twice as fast as other Elixir/Erlang libraries (most notably Poison). The performance is comparable to jiffy, which is implemented in C as a NIF. Jason is usually only twice as slow. Both the parser and generator fully conform to RFC 8259 and ECMA 404 standards. The parser is tested using JSONTestSuite. The package can be installed by adding jason to your list of dependencies in mix.exs. Jason...
