Search Results for "language" - Page 49
Sort By:
Showing 2019 open source projects for "language"
View related business solutions-
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.
-
$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.
-
1
SMC - The State Machine Compiler
Translates state machine into a target programming language.
SMC takes a state machine stored in a .sm file and generates a State pattern in 14 programming languages. Includes: default transitions, transition args, transition guards, push/pop transitions and Entry/Exit actions. See User Manual for more info. -
2
pyllama
LLaMA: Open and Efficient Foundation Language Models
📢 pyllama is a hacked version of LLaMA based on original Facebook's implementation but more convenient to run in a Single consumer grade GPU. -
3
Bot on Anything
Large model-based chatbot builder that can quickly integrate AI models
Bot on Anything is a versatile open-source AI chatbot builder that lets developers connect large language models such as ChatGPT, Claude, and Gemini to virtually any messaging platform, website, or interface with minimal configuration. At its heart, the project abstracts away the glue logic between AI model APIs and disparate application “channels,” enabling the same bot logic to run in Slack, Telegram, Gmail, enterprise tools, web UIs, or command-line terminals. -
4
Simple LLM Finetuner
Simple UI for LLM Model Finetuning
Simple LLM Finetuner is a beginner-friendly interface designed to make the process of fine-tuning large language models more accessible by providing a simplified UI and workflow built around parameter-efficient techniques such as LoRA. It allows users to customize pre-trained models using relatively small datasets and modest hardware, making it feasible to experiment with LLM training even on consumer-grade GPUs or cloud environments like Google Colab. -
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
5
GPT-NeoX
Implementation of model parallel autoregressive transformers on GPUs
This repository records EleutherAI's library for training large-scale language models on GPUs. Our current framework is based on NVIDIA's Megatron Language Model and has been augmented with techniques from DeepSpeed as well as some novel optimizations. We aim to make this repo a centralized and accessible place to gather techniques for training large-scale autoregressive language models, and accelerate research into large-scale training. -
6
Orchest
Build data pipelines, the easy way
...Run scripts or Jupyter notebooks as steps in a pipeline. Python, R, Julia, JavaScript, and Bash are supported. Parameterize your pipelines and run them periodically on a cron schedule. Easily install language or system packages. Built on top of regular Docker container images. Creation of multiple instances with up to 8 vCPU & 32 GiB memory. A free Orchest instance with 2 vCPU & 8 GiB memory. Simple data pipelines with Orchest. Each step runs a file in a container. It's that simple! Spin up services whose lifetime spans across the entire pipeline run. ... -
7
MLPACK is a C++ machine learning library with emphasis on scalability, speed, and ease-of-use. Its aim is to make machine learning possible for novice users by means of a simple, consistent API, while simultaneously exploiting C++ language features to provide maximum performance and flexibility for expert users. * More info + downloads: https://mlpack.org * Git repo: https://github.com/mlpack/mlpack
-
8
KAGSA
KAGSA PROGRAMMING LANGUAGE
it designed to be easy to learn and practical for use in various projects. It has a flexible syntax and allows some things that other languages prohibit, such as using certain symbols in variable names and starting variable names with numbers. KAGSA contains several main components, including a lexer, syntax checker, parser, and compiler. It supports object-oriented programming, iteration, and other features commonly used in programming languages. -
9
Alpa
Training and serving large-scale neural networks
Alpa is a system for training and serving large-scale neural networks. Scaling neural networks to hundreds of billions of parameters has enabled dramatic breakthroughs such as GPT-3, but training and serving these large-scale neural networks require complicated distributed system techniques. Alpa aims to automate large-scale distributed training and serving with just a few lines of code. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
PromptCraft-Robotics
Community for applying LLMs to robotics and a robot simulator
The PromptCraft-Robotics repository serves as a community for people to test and share interesting prompting examples for large language models (LLMs) within the robotics domain. We also provide a sample robotics simulator (built on Microsoft AirSim) with ChatGPT integration for users to get started. We currently focus on OpenAI's ChatGPT, but we also welcome examples from other LLMs (for example open-sourced models or others with API access such as GPT-3 and Codex). -
11
Vimspector
A multi-language debugging system for Vim
vimspector is a powerful debugging plugin for Vim and Neovim designed to bring IDE-style debugging capabilities (breakpoints, stepping, call stacks, watch windows) into the modal editor world. It supports multiple languages (C++, Python, TCL among others) via the Debug Adapter Protocol (DAP) model and provides an in-editor UI for viewing scopes, variables, stack frames, output windows and more. You configure it per-project via a .vimspector.json file (or per file type) specifying the... -
12
nanogpt-lecture
Code created in the Neural Networks: Zero To Hero video lecture
...It therefore serves as a practical bridge between introductory language modeling and larger GPT implementations. -
13
ImPromptu
Domain Agnostic Prompts for Savvy Professionals
A community-driven wiki of sorts full of your favorite prompts for various Large Language Models such as ChatGPT, GPT-3, MidJourney, and soon (Google's Bard) and more! Choose a subject area you are interested in, and click the link below to go to the page with prompts for that subject. If that page is empty, then you can help by adding prompts to that page. If you are not sure how to do that, you can read the contributing guidelines. -
14
Classic HWUT
Software Unit Tests (Language Independent Approach)
Automation of Unit and System Tests. Tests can be implemented in any language and on many platforms. The flexible approach enables the inclusion of many types of tests, such as memory leak checks (using valgrind), coding rule checks, complexity checks, etc. Tests are run by a simple call to hwut in a base directory of a project. In particular for C, HWUT supports make file generation using 'sos' and 'sols' modes. -
15
guiscrcpy
Full fledged GUI integration for the Android screen mirroring system
A simple, pluggable, graphical user interface for the fastest Android screen mirroring software, scrcpy. guiscrcpy is a multiplatform, ready-to-use GUI layer for Android to PC screen mirroring written in the advancing programming language python3 for the most award-winning open-source android screen mirroring system. -
16
PhoenixC2
Command & Control-Framework created for collaboration in python3
PhoenixC2 is a command & control framework. The purpose of this software is, to aid red teamers and penetration testers in their operations, by providing a way to manage hacked devices. -
17
CPT
CPT: A Pre-Trained Unbalanced Transformer
A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation. We replace the old BERT vocabulary with a larger one of size 51271 built from the training data, in which we 1) add missing 6800+ Chinese characters (most of them are traditional Chinese characters); 2) remove redundant tokens (e.g. Chinese character tokens with ## prefix); 3) add some English tokens to reduce OOV. -
18
TextBox
A text generation library with pre-trained language models github.com
TextBox 2.0 is an up-to-date text generation library based on Python and PyTorch focusing on building a unified and standardized pipeline for applying pre-trained language models to text generation. From a task perspective, we consider 13 common text generation tasks such as translation, story generation, and style transfer, and their corresponding 83 widely-used datasets. From a model perspective, we incorporate 47 pre-trained language models/modules covering the categories of general, translation, Chinese, dialogue, controllable, distilled, prompting, and lightweight models (modules). ... -
19
Komodo Edit
Komodo Edit is a fast and free multi-language code editor
Code faster with the IDE for today’s web languages – Python, PHP, Perl, Golang, Ruby, and more. Powerful editor with syntax highlighting, autocomplete, code refactoring, and more. Visual debugger and more to debug, inspect, and test your code. Support for Git, Mercurial, Subversion, CVS, Perforce and Bazaar. Tons of add-ons for customizing and extending features. Great tools for pair programming and collaboration. Python, PHP, Perl, Go, Ruby, Node.js, JavaScript, and more. Define your own... -
20
minGPT
A minimal PyTorch re-implementation of the OpenAI GPT
minGPT is a minimalist, educational re-implementation of the GPT (Generative Pretrained Transformer) architecture built in PyTorch, designed by Andrej Karpathy to expose the core structure of a transformer-based language model in as few lines of code as possible. It strips away extraneous bells and whistles, aiming to show how a sequence of token indices is fed into a stack of transformer blocks and then decoded into the next token probabilities, with both training and inference supported. Because the whole model is around 300 lines of code, users can follow each step—from embedding lookup, positional encodings, multi-head attention, feed-forward layers, to output heads—and thus demystify how GPT-style models work beneath the surface. ... -
21
footswitch3
Audio Transcription software for Linux (Gstreamer) with a foot pedal
Footswitch 3 is a media player for transcribers on Linux. Written in python using the python bindings for Gstreamer it allows a transcriber to control the audio or video with a foot pedal, and includes a set of macros that integrate into LibreOffice. This allows the transcriber to control the media player from within Libreoffice as well, making it useful for those who do not yet own a foot pedal/foot switch. Control of the media player from LibreOffice can be via Hotkeys or an integrated... -
22
SBEVSL is a collaborative project between Dowling and RIT on the development of a Structural Biology Extensible Visualization Scripting Language, so that users can move freely among various molecular graphics tools, such as rasmol, pymol, raster3d, etc.
-
23
cerche
Experimental search engine for conversational AI such as parl.ai
This is an experimental search engine for conversational AI such as parl.ai, large language models such as OpenAI GPT3, and humans (maybe). -
24
d2l-zh
Chinese-language edition of Dive into Deep Learning
d2l‑zh is the Chinese-language edition of Dive into Deep Learning, an interactive, open‑source deep learning textbook that combines code, math, and explanatory text. It features runnable Jupyter notebooks compatible with multiple frameworks (e.g., PyTorch, MXNet, TensorFlow), comprehensive theoretical analysis, and exercises. Widely adopted in over 70 countries and used by more than 500 universities for teaching deep learning. -
25
Scripting Language Bindings
A port of WFOPT to the several scripting languages
This project contains bindings for various scripting languages to the Wheefun Options Parsing Library. It is meant to provide parity with the C implementation so .NET languages can take advantage of WFOPT. For more information, please see the main page.
