Search Results for "mt-32"
Sort By:
154 projects for "mt-32" with 1 filter applied:
-
Easily Host LLMs and Web Apps on Cloud RunRun frontend and backend services, batch jobs, host LLMs, and queue processing workloads without the need to manage infrastructure. Cloud Run gives you on-demand GPU access for hosting LLMs and running real-time AI—with 5-second cold starts and automatic scale-to-zero so you only pay for actual usage. New customers get $300 in free credit to start.
-
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.
-
1
HY-MT
Hunyuan Translation Model Version 1.5
HY-MT (Hunyuan Translation) is a high-quality multilingual machine translation model suite developed to support mutual translation across dozens of languages with strong performance even at smaller model scales. It ships with both an 1.8 B parameter model and a larger 7 B model, the latter optimized not only for direct translation but also for formatted and contextualized output, allowing better handling of terminology and mixed-language content. -
2
Kimi K2
Kimi K2 is the large language model series developed by Moonshot AI
Kimi K2 is Moonshot AI’s advanced open-source large language model built on a scalable Mixture-of-Experts (MoE) architecture that combines a trillion total parameters with a subset of ~32 billion active parameters to deliver powerful and efficient performance on diverse tasks. It was trained on an enormous corpus of over 15.5 trillion tokens to push frontier capabilities in coding, reasoning, and general agentic tasks while addressing training stability through novel optimizer and architecture design strategies. The model family includes variants like a foundational base model that researchers can fine-tune for specific use cases and an instruct-optimized variant primed for general-purpose chat and agent-style interactions, offering flexibility for both experimentation and deployment. ... -
3
1D Visual Tokenization and Generation
This repo contains the code for 1D tokenizer and generator
The 1D Visual Tokenization and Generation project from ByteDance introduces a novel “one-dimensional” tokenizer designed for images: instead of representing images with large grids of 2D tokens (as in many prior generative/image-modeling systems), it compresses images into as few as 32 discrete tokens (or more, optionally) — thereby achieving a very compact, efficient representation that drastically speeds up generation and reconstruction while retaining strong fidelity. This compact representation makes sampling and generation many times faster compared to previous tokenization methods (claims of ~410× speedups relative to heavyweight models) while still producing competitive image quality. ... -
4
os-tutorial
How to create an OS from scratch
os-tutorial is an open source educational project by cfenollosa that teaches the basics of building an operating system from scratch. The repository provides step-by-step lessons starting with bootloaders and moving through kernel development, interrupts, memory management, and system calls. Each tutorial is accompanied by clear explanations, code examples, and references to deepen understanding. The project uses x86 assembly and C to illustrate concepts, making it accessible to students and... -
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI Studio. Switch between models without switching platforms.
-
5
LibChecker
An app to view libraries used in apps in your device
This app is used to view the third-party libraries used by applications in your device. It can view the ABI architecture of the application's native library (in general, whether the application is 64-bit or 32-bit). It can also view well-known libraries marked by The Rule Repository, and can even sort and view them according to the number of libraries references. -
6
FLUX.2
Official inference repo for FLUX.2 models
FLUX.2 is a state-of-the-art open-weight image generation and editing model released by Black Forest Labs aimed at bridging the gap between research-grade capabilities and production-ready workflows. The model offers both text-to-image generation and powerful image editing, including editing of multiple reference images, with fidelity, consistency, and realism that push the limits of what open-source generative models have achieved. It supports high-resolution output (up to ~4 megapixels),... -
7
GLM-4.5
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
GLM-4.5 is a cutting-edge open-source large language model designed by Z.ai for intelligent agent applications. The flagship GLM-4.5 model has 355 billion total parameters with 32 billion active parameters, while the compact GLM-4.5-Air version offers 106 billion total parameters and 12 billion active parameters. Both models unify reasoning, coding, and intelligent agent capabilities, providing two modes: a thinking mode for complex reasoning and tool usage, and a non-thinking mode for immediate responses. They are released under the MIT license, allowing commercial use and secondary development. ... -
8
xlswriter
PHP Extension for creating and reader XLSX files
PHPExcel has been unable to work properly for memory reasons at 40,000 and 100000 points, but it can be resolved by modifying the ini configuration, but the time may take longer to complete the work. xlswriter is a PHP C Extension that can be used to write text, numbers, formulas and hyperlinks to multiple worksheets in an Excel 2007+ XLSX file. -
9
bitnet.cpp
Official inference framework for 1-bit LLMs
...At its core is bitnet.cpp, a highly optimized C++ backend that supports fast, low-memory inference on both CPUs and GPUs, enabling models such as BitNet b1.58 to run without requiring enormous compute infrastructure. The project’s focus on extreme quantization dramatically reduces memory footprint and energy consumption compared with traditional 16-bit or 32-bit LLMs, making it practical to deploy advanced language understanding and generation models on everyday machines. BitNet is built to scale across architectures, with configurable kernels and tiling strategies that adapt to different hardware, and it supports large models with impressive throughput even on modest resources. -
AI-generated apps that pass security reviewRetool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.
-
10
Prowide Core
Java framework for SWIFT [tm] MT (FIN) messaging
Prowide Core (previously known as WIFE) is an open source Java framework for managing SWIFT MT messages. The library key features are the comprehensive Java model for all MT message types, along a straight-forward parsing and building API. The project is active since 2006, production ready and commercially supported. For detail information on the support package options please check: https://www.prowidesoftware.com/services SWIFT is a trademark of S.W.I.F.T. ... -
11
Develop EFI applications for ARM-64, ARM-32, x86_64, IA-64 (IPF), IA-32 (x86), and MIPS platforms using the GNU toolchain and the EFI development environment.
-
12
Code World Model (CWM)
Research code artifacts for Code World Model (CWM)
CWM (Code World Model) is a 32-billion-parameter open-weights language model. It is developed by Meta for enhancing code generation and reasoning about programs. It is explicitly trained on execution traces, action-observation trajectories, and agentic interactions in controlled environments. It has been developed to better capture how code, actions, and state interact over time. -
13
fast_float
Implementation of the C++ from_chars functions for number types
The fast_float library provides fast header-only implementations for the C++ from_chars functions for float and double types as well as integer types. These functions convert ASCII strings representing decimal values (e.g., 1.3e10) into binary types. We provide exact rounding (including round to even). In our experience, these fast_float functions many times faster than comparable number-parsing functions from existing C++ standard libraries. It parses the character sequence [first,last) for... -
14
frugally-deep
A lightweight header-only library for using Keras (TensorFlow) models
Use Keras models in C++ with ease. A lightweight header-only library for using Keras (TensorFlow) models in C++. Works out-of-the-box also when compiled into a 32-bit executable. (Of course, 64 bit is fine too.) Avoids temporarily allocating (potentially large chunks of) additional RAM during convolutions (by not materializing the im2col input matrix). Utterly ignores even the most powerful GPU in your system and uses only one CPU core per prediction. Quite fast on one CPU core, and you can run multiple predictions in parallel, thus utilizing as many CPUs as you like to improve the overall prediction throughput of your application/pipeline. -
15
A multi-platform software synthesiser emulating (somewhat inaccurately) pre-GM MIDI devices such as the Roland MT-32, CM-32L, CM-64 and LAPC-I. In no way endorsed by or affiliated with Roland Corp. Source hosted at: http://www.github.com/munt/
-
16
FLUX.1 Krea
Powerful open source image generation model
...It is a rectified-flow model distilled from the original Krea 1, providing enhanced sampling efficiency through classifier-free guidance distillation. The model supports generation at resolutions between 1024 and 1280 pixels with recommended inference steps between 28 and 32 for optimal balance of speed and quality. FLUX.1 Krea is fully compatible with the FLUX.1 architecture, making it easy to integrate into existing workflows and pipelines. The repository offers easy-to-use inference scripts and a Jupyter Notebook example to facilitate quick experimentation and adoption. Users can run the model locally after downloading weights from Hugging Face and benefit from a live demo available on krea.ai. -
17
wkpu
Encrypted processor based on public RISC processor
...This implementation of the `KPU' encrypted computing model makes no changes to the standard RISCV processor core other than broadening all paths to 128 bits instead of 32/64. It works instead via additional peripheral units and extra custom RISCV instructions. -
18
GLM-4-32B-0414
Open Multilingual Multimodal Chat LMs
GLM-4-32B-0414 is a powerful open-source large language model featuring 32 billion parameters, designed to deliver performance comparable to leading models like OpenAI’s GPT series. It supports multilingual and multimodal chat capabilities with an extensive 32K token context length, making it ideal for dialogue, reasoning, and complex task completion. The model is pre-trained on 15 trillion tokens of high-quality data, including substantial synthetic reasoning datasets, and further enhanced with reinforcement learning and human preference alignment for improved instruction-following and function calling. ... -
19
BioXTAS RAW
Processing and analysis of Small Angle X-ray Scattering (SAXS) data.
BioXTAS RAW is a program for analysis of Small-Angle X-ray Scattering (SAXS) data. The software enables: creation of 1D scattering profiles from 2D detector images, standard data operations such as averaging and subtraction, analysis of radius of gyration (Rg) and molecular weight, and advanced analysis using GNOM and DAMMIF as well as electron density reconstructions using DENSS. It also allows easy processing of inline SEC-SAXS data and data deconvolution using the evolving factor analysis... -
20
belofte chess
A promising chess program
...Belofte 0.2.0 till 0.9.20 (c/c++): Xboard 1 & 2 (CECP) - Linux/Unix/(Windows) Belofte 2.1.1 and up (c++11) : UCI and Xboard 2 - Linux/Windows/Mac/Android/... For access to code, please clone the git repository. Compiles and Runs on 32/64 bit on Windows, Mac, Linux, Android (ARM/x86) and Raspberry. Released under GNU v2 license. (means free to copy, free to modify, free to use, ...) Works fine with Arena/Cutechess/BanksiaGui/Winboard/Xboard/... -
21
Ficl is a lightweight, embeddable scripting language designed to be incorporated into other programs, and especially embedded systems that may have memory and OS constraints. Applications include scripting, hardware bring-up, rapid prototyping, and system extensions. Unlike Lua or Python, Ficl acts as a component of your system - you feed it stuff to do, it does the stuff, and comes back to you for more. You can export compiled code to Ficl, execute Ficl code from your compiled code, or...
-
22
M32/X32 Show Manager
Reorganize M32/X32 show files
Both the Midas M32 and Behringer X32 share the same design of show management using the console GUI, M32-Edit and X32-Edit apps. This app provides an alternative method to manage these show files (cues, scenes and snippets). It provides an easier method of reorganizing and importing/exporting of files. -
23
Unreal Speccy portable
Portable ZX-Spectrum emulator based on UnrealSpeccy 0.37.3 by SMT
Portable ZX-Spectrum emulator supports Z80 128K (Pentagon) AY/YM, Beeper, Beta Disk, Tape, Kempston Joystick/Mouse, Snapshots, Replays. Supported formats: sna, z80, szx, rzx, tap, tzx, csw, trd, scl, fdi, zip. Created to be ported to many platforms such as Windows/Linux/Mac/Symbian/Dingoo A320/Android/iOS/PSP/Raspberry Pi, ... -
24
grafx - Extensible Java Graphics Package
Extensible Line-drawing & Polygon-filling Rasterization Libs for Java
...Suitable for study in academic institutions, especially as related to line-drawing accuracy. Particular attention to detail concerning chopping of accumulation errors, using a cast from 64 bit to 32 bit strategy, in the interval [1.0,2.0). Individual pixel errors with overlapping polygons or line segments are about one in a billion, but I can't reproduce any errors at the moment by using random number generation with tens of millions of cases. Emphasis not only on correctness, but also on performance for real-world use or hardware implementation. -
25
BJH OS
An Operating System Created In Html CSS And JS By Muhammad Haris.
💻 BJH OS Assalam O Alaikum! 👋 I’m Muhammad Haris, Developer of BJH OS 🌐💡 — a web-based OS built with pure HTML, CSS & JS. Enjoy draggable windows, built-in apps, a web terminal, Flash Browser, AI assistant, and persistent data via localStorage. 🚀 Highlights Custom desktop environment & smoother UI Modular architecture Built-in apps & BJH OS Apps Market Remote alerts & updates Secure login & developer tools 🛒 BJH OS Apps Market Features Browse apps/games App details: icon,...
