Search Results for "compare" - Page 2
Sort By:
Showing 128 open source projects for "compare"
View related business solutions-
Field Service+ for MS Dynamics 365 & SalesforceResco’s mobile solution streamlines your field service operations with offline work, fast data sync, and powerful tools for frontline workers, all natively integrated into Dynamics 365 and Salesforce.
-
Skillfully - The future of skills based hiringSkillfully transforms hiring through AI-powered skill simulations that show you how candidates actually perform before you hire them. Our platform helps companies cut through AI-generated resumes and rehearsed interviews by validating real capabilities in action. Through dynamic job specific simulations and skill-based assessments, companies like Bloomberg and McKinsey have cut screening time by 50% while dramatically improving hire quality.
-
1
Advanced RAG Techniques
Advanced techniques for RAG systems
...It includes hands-on Jupyter notebooks and runnable scripts that show how to implement ideas like optimizing chunk sizes, proposition chunking, HyDE/HyPE query transformations, fusion retrieval, reranking, and ensemble retrieval. There is also an evaluation section that demonstrates how to measure RAG performance and compare different configurations in a systematic way. -
2
Pearl
A Production-ready Reinforcement Learning AI Agent Library
...Tutorials demonstrate end-to-end workflows on OpenAI Gym tasks and contextual-bandit setups derived from tabular datasets, emphasizing reproducibility and clear baselines. Pearl’s design favors clarity and deployability: metrics, logging, and evaluation harnesses are integrated so you can monitor learning, compare agents, and catch regressions. -
3
imgclsmob Deep learning networks
Sandbox for training deep learning networks
...Several deep learning frameworks are supported, allowing researchers to experiment with architectures in different environments. The project is frequently used by developers who want to study modern convolutional neural network designs and compare their performance across datasets. -
4
D4RL
Collection of reference environments, offline reinforcement learning
...The API is based on Gymnasium (via gym.make) and each environment also exposes a method get_dataset() that returns the offline data to learn from. The repository emphasizes open science, reproducibility, and benchmarking at scale, making it easier to compare algorithms on equal footing. -
Award-Winning Medical Office Software Designed for Your SpecialtyRXNT is an ambulatory healthcare technology pioneer that empowers medical practices and healthcare organizations to succeed and scale through innovative, data-backed, AI-powered software.
-
5
rate.sx
Curl cryptocurrencies exchange rates
...It emphasizes human-readable output by default, with options for concise one-liners or richer summaries including sparkline-style ASCII charts. The service supports multiple coins, fiat conversions, and historical lookups so you can compare prices over time without leaving the terminal. Under the hood it aggregates price feeds and normalizes the results for robust querying, yet keeps the interface dead simple. Because it’s HTTP-based, you can integrate it into shell prompts, tmux status lines, CI logs, dashboards, or chat bots. It’s ideal for developers and power users who want quick answers and scriptable endpoints without installing a heavy client. -
6
aisuite
Simple, unified interface to multiple Generative AI providers
Simple, unified interface to multiple Generative AI providers. aisuite makes it easy for developers to use multiple LLM through a standardized interface. Using an interface similar to OpenAI's, aisuite makes it easy to interact with the most popular LLMs and compare the results. It is a thin wrapper around Python client libraries and allows creators to seamlessly swap out and test responses from different LLM providers without changing their code. Today, the library is primarily focused on chat completions. We will expand it to cover more use cases in the near future. Currently supported providers are - OpenAI, Anthropic, Azure, Google, AWS, Groq, Mistral, HuggingFace and Ollama. ... -
7
EasyR1
An Efficient, Scalable, Multi-Modality RL Training Framework
...It emphasizes memory-efficient training strategies so you can train long-context or reasoning-dense models on commodity GPUs. The framework is also organized to help you compare training strategies (e.g., pure SFT vs. preference optimization) so you can see what actually moves metrics in math, code, and multi-step reasoning. For teams exploring open reasoning models, EasyR1 provides an opinionated yet flexible path from dataset to deployable checkpoints. -
8
KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
...KVCache-Factory provides a platform for implementing and evaluating multiple compression strategies that reduce memory usage while preserving model performance. The framework integrates several state-of-the-art methods such as PyramidKV, SnapKV, H2O, and StreamingLLM, allowing researchers to compare and experiment with different approaches within the same environment. It also supports advanced inference configurations such as Flash Attention v2 and multi-GPU inference setups for very large models. -
9
Hallucination Leaderboard
Leaderboard Comparing LLM Performance at Producing Hallucinations
...Each model is tested on document summarization tasks to measure how often generated responses introduce information that is not supported by the original source material. The results are published as a leaderboard that allows researchers and developers to compare model reliability and factual consistency. By focusing on hallucination rates rather than traditional metrics such as accuracy or fluency, the benchmark highlights an important aspect of AI system safety and trustworthiness. The leaderboard is regularly updated as new models are released and evaluation methods evolve. -
The AI workplace management platformBy combining AI workflows, predictive intelligence, and automated insights, OfficeSpace gives leaders a complete view of how their spaces are used and how people work. Facilities, IT, HR, and Real Estate teams use OfficeSpace to optimize space utilization, enhance employee experience, and reduce portfolio costs with precision.
-
10
Unstract
No-code LLM Platform to launch APIs and ETL Pipelines
Unstract is a powerful open-source, no-code platform built to automate the extraction and structuring of unstructured documents using large language models and flexible workflows, enabling developers and data teams to turn messy files into organized JSON content without complex coding. It integrates a visual Prompt Studio environment where users can iteratively design extraction schemas, compare outputs from different models, and monitor costs and accuracy side by side, making it easier to refine prompts and extraction logic before deploying at scale. Unstract supports deploying structured extraction as REST API endpoints or embedding it into data engineering ETL pipelines, which allows it to plug directly into data warehouses, cloud storage, or downstream analytics systems. ... -
11
Lingvo
Framework for building neural networks
...Lingvo includes reference models and configurations for domains like machine translation, automatic speech recognition, language modeling, image understanding, and 3D object detection. Centralized hyperparameter configuration files allow researchers to share exact experiment setups so others can retrain and compare results reliably. -
12
Multimodal
TorchMultimodal is a PyTorch library
...The design emphasizes composability: you can mix and match encoder, fusion, and decoder components rather than starting from monolithic models. The repository also includes example scripts and datasets for common multimodal tasks (e.g. retrieval, visual question answering, grounding) so you can test and compare models end to end. Installation supports both CPU and CUDA, and the codebase is versioned, tested, and maintained. -
13
xFormers
Hackable and optimized Transformers building blocks
xformers is a modular, performance-oriented library of transformer building blocks, designed to allow researchers and engineers to compose, experiment, and optimize transformer architectures more flexibly than monolithic frameworks. It abstracts components like attention layers, feedforward modules, normalization, and positional encoding, so you can mix and match or swap optimized kernels easily. One of its key goals is efficient attention: it supports dense, sparse, low-rank, and... -
14
TensorBoardX
tensorboard for pytorch (and chainer, mxnet, numpy, etc.)
...This allows a training program to call methods to add data to the file directly from the training loop, without slowing down training. TensorboardX now supports logging directly to Comet. Comet is a free cloud based solution that allows you to automatically track, compare and explain your experiments. It adds a lot of functionality on top of tensorboard such as dataset management, diffing experiments, seeing the code that generated the results and more. Create special chart by collecting charts tags in ‘scalars’. Note that this function can only be called once for each SummaryWriter() object. Because it only provides metadata to tensorboard, the function can be called before or after the training loop. -
15
Evals
Evals is a framework for evaluating LLMs and LLM systems
The openai/evals repository is a framework and registry for evaluating large language models and systems built with LLMs. It’s designed to let you define “evals” (evaluation tasks) in a structured way and run them against different models or agents, with the ability to score, compare, and analyze results. The framework supports templated YAML eval definitions, solver-based evaluations, custom metrics, and composition of multi-step evaluations. It includes utilities and APIs to plug in completion functions, manage prompts, wrap retries or error handling, and register new evaluation types. It also maintains a growing registry of standard benchmarks or “evals” that users can reuse (for example, tasks measuring reasoning, factual accuracy, or chain-of-thought capabilities). ... -
16
Lightweight' GAN
Implementation of 'lightweight' GAN, proposed in ICLR 2021
...You should expect it to be 33% faster and save up to 40% memory. Aim is an open-source experiment tracker that logs your training runs, and enables a beautiful UI to compare them. -
17
Prompt Engineering Interactive Tutorial
Anthropic's Interactive Prompt Engineering Tutorial
...Lessons include building prompts from scratch for common tasks like extraction, classification, transformation, and step-by-step reasoning, with checkpoints that let you compare your outputs against solid baselines. You’ll also practice advanced patterns such as tool use, constrained generation, and response validation so outputs are trustworthy and machine-consumable. -
18
Canopy
Retrieval Augmented Generation (RAG) framework
...Developers can use Canopy to quickly build chat systems that answer questions using their own data instead of relying solely on the pretrained knowledge of the language model. The framework includes a built-in server and command-line interface that allow users to experiment with RAG pipelines and compare outputs between retrieval-augmented responses and standard LLM responses. -
19
CompareDir
Tool to Compare 2 directories and handle the files.
...It does not compute md5 sums because that would make it extremely slow. Mind you i use this regular for directories with 2000 photos. Based on Python, pygobject and gtk3. + Python-pillow if you want to compare 2 images. No installation: untar -xvzf CompareDir.tgz where you want and run. -
20
Nexa is an advanced tool that's used to parse and compare Ericsson XML files (mainly the 3GPP version). This tool can plot RF data as well as sites and cells, making it very handy for day-to-day operations. Current functions: 1. Pare BSC/RNC/4G/5G/IoT XML files from Ericsson. 2. Compare the configuration of the selected XML files. 3. Generate the Bulk-Configuration files. 4. Plot KML maps for daily use.
-
21
PyCheck
Calculates the checksum of a file, and compares it to an original.
PyCheck calculates the checksum of a file, and compares it to an original either by selecting an original copy of the file, or manually entering the checksum of the original file, such as when it is provided on a website from which you downloaded a file. In Linux this program depends on the Python3 TK package, so make sure you have python3-tk installed using your distribution's package manager before continuing. I digitally sign some files in my releases. If you'd like to verify those... -
22
LLaVA
Visual Instruction Tuning: Large Language-and-Vision Assistant
Visual instruction tuning towards large language and vision models with GPT-4 level capabilities. -
23
Arianne RPG
Arianne is an engine to develop multiplayer online games like Stendhal
...With hundreds of NPCs and different quests, features like the Travel log and achievement system keep track of progress. Thousands of creatures are ready to fight, above and below ground, and as players level up they can compare themselves on a detailed stats website. The engine Marauroa provides a simple way of creating games on a portable and robust server architecture. Marauroa manages the client server communication and provides an object orientated view of the world for game developers. It handles database access in a transparent way to store player accounts, character progress and the state of the world -
24
CiteFlow
Desktop research workspace for PDFs, notes, citations, bibliographies.
...Create project-based workspaces for essays, articles, reports, literature reviews, and long-form research. Import PDFs, read them inside the app, search within documents, compare files side by side, highlight key passages, and add page-based notes. CiteFlow can assist with DOI metadata detection, keeps citation history linked to copied text, and generates citations and bibliographies in APA 7 and MLA 9. OCR support helps make scanned PDFs searchable, while project-wide search helps you find matching text across PDFs, highlights, and notes. ... -
25
GNNPCSAFT Web App
Smart Thermodynamic Modeling with Graph Neural Networks
...We developed this app so the scientific community can access the model's results easily. In this app, the estimated pure-component parameters can be used to calculate thermodynamic properties and compare them with experimental data from the ThermoML Archive. More info on github repository.
