Search Results for "tiny-tex"
Sort By:
Showing 28 open source projects for "tiny-tex"
View related business solutions-
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.
-
Build AI Apps with Gemini 3 on Vertex AIVertex AI gives developers access to Gemini 3—Google’s most advanced reasoning and coding model—plus 200+ foundation models including Claude, Llama, and Gemma. Build generative AI apps with Vertex AI Studio, customize with fine-tuning, and deploy to production with enterprise-grade MLOps. New customers get $300 in free credits.
-
1
Tiny CUDA Neural Networks
Lightning fast C++/CUDA neural network framework
...It will likely only work on an RTX 3090, an RTX 2080 Ti, or high-end enterprise GPUs. Lower-end cards must reduce the n_neurons parameter or use the CutlassMLP (better compatibility but slower) instead. tiny-cuda-nn comes with a PyTorch extension that allows using the fast MLPs and input encodings from within a Python context. These bindings can be significantly faster than full Python implementations; in particular for the multiresolution hash encoding. -
2
ChatGPT Academic
ChatGPT extension for scientific research work
...Support for markdown tables output by GPT. If the output contains a formula, it will be displayed in tex form and rendered form at the same time, which is convenient for copying and reading. -
3
SillyTavern
LLM Frontend for Power Users
Mobile-friendly, Multi-API (KoboldAI/CPP, Horde, NovelAI, Ooba, OpenAI, OpenRouter, Claude, Scale), VN-like Waifu Mode, Horde SD, System TTS, WorldInfo (lorebooks), customizable UI, auto-translate, and more prompt options than you'd ever want or need. Optional Extras server for more SD/TTS options + ChromaDB/Summarize. SillyTavern is a user interface you can install on your computer (and Android phones) that allows you to interact with text generation AIs and chat/roleplay with characters... -
4
DeiT (Data-efficient Image Transformers)
Official DeiT repository
...Its key idea is a specialized distillation strategy—including a learnable “distillation token”—that lets a transformer learn effectively from a CNN or transformer teacher on modest-scale datasets. The project provides compact ViT variants (Tiny/Small/Base) that achieve excellent accuracy–throughput trade-offs, making transformers practical beyond massive pretraining regimes. Training involves carefully tuned augmentations, regularization, and optimization schedules to stabilize learning and improve sample efficiency. The repo offers pretrained checkpoints, reference scripts, and ablation studies that clarify which ingredients matter most for data-efficient ViT training. -
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.
-
5
Quadratic
Data science spreadsheet with Python & SQL
...Quadratic has Python library support built-in. Bring the latest open-source tools directly to your spreadsheet. Quickly write code and see the output in full detail. No more squinting into a tiny terminal to see your data output. -
6
MimicLaw
Run OpenClaw on a $5 chip
MimiClaw (from the mimiclaw project) is an edge-AI personal assistant that runs directly on extremely low-cost hardware like an ESP32-S3 microcontroller without a full operating system, Node.js, or cloud backend. By running pure C on a bare-metal chip, MimiClaw brings AI interactions and persistent memory to a tiny USB-powered device you can carry in your pocket. You connect the device to Wi-Fi and chat with it using Telegram, making it a convenient always-on assistant for tasks like reminders, quick lookups, or custom AI interactions. Even though it’s running on minimal hardware, MimiClaw maintains local memory that persists across power cycles, enabling context continuity over time without relying on cloud services. ... -
7
Magika
Fast and accurate AI powered file content types detection
Magika is an AI-powered file-type detector that uses a compact deep-learning model to classify binary and textual files with high accuracy and very low latency. The model is engineered to be only a few megabytes and to run quickly even on CPU-only systems, making it practical for desktop apps, servers, and security pipelines. Magika ships as a command-line tool and a library, providing drop-in detection that improves on traditional “magic number” and heuristic approaches, especially for... -
8
LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
...The repository favors clear Python and NumPy or PyTorch implementations that can be run and modified without heavyweight frameworks obscuring the logic. Chapters and notebooks progress from tiny toy models to more capable transformer stacks, including sampling strategies and evaluation hooks. The focus is on readability, correctness, and experimentation, making it ideal for students and practitioners transitioning from theory to working systems. By the end, you have a grounded sense of how data pipelines, optimization, and inference interact to produce fluent text. -
9
llm.c
LLM training in simple, raw C/CUDA
llm.c is a minimalist, systems-level implementation of a small transformer-based language model in C that prioritizes clarity and educational value. By stripping away heavy frameworks, it exposes the core math and memory flows of embeddings, attention, and feed-forward layers. The code illustrates how to wire forward passes, losses, and simple training or inference loops with direct control over arrays and buffers. Its compact design makes it easy to trace execution, profile hotspots, and... -
Run Any Workload on Compute Engine VMsCompute Engine delivers high-performance virtual machines for web apps, databases, containers, and AI workloads. Choose from general-purpose, compute-optimized, or GPU/TPU-accelerated machine types—or build custom VMs to match your exact specs. With live migration and automatic failover, your workloads stay online. New customers get $300 in free credits.
-
10
Moondream
Tiny vision language model
Moondream is a creative code project and visual experimentation repository that explores generative graphics, aesthetic patterns, and interactive art through code. The project typically showcases procedural visualizations, algorithmic designs, and artistic experiments that push the boundaries of what can be expressed with programming languages and rendering frameworks. While the exact nature can vary by commit or branch, Moondream’s work often blends geometry, color theory, and motion to... -
11
Z80-μLM
Z80-μLM is a 2-bit quantized language model
Z80-μLM is a retro-computing AI project that demonstrates a tiny language model (Z80-μLM) engineered to run on an 8-bit Z80 CPU by aggressively quantizing weights down to 2-bit precision. The repository provides a complete workflow where you train or fine-tune conversational models in Python, then export them into a format that can be executed on classic Z80 systems. A key deliverable is producing CP/M-compatible .COM binaries, enabling a genuinely vintage “chat with your computer” experience on real hardware or accurate emulators. ... -
12
FastAPI-MCP
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools
...The server speaks directly to your app over its ASGI interface, avoiding extra HTTP hops between the MCP layer and your API, which reduces latency and simplifies deployment. A tiny bootstrap is enough to stand up an MCP server and, if desired, mount an HTTP transport for remote clients. The docs emphasize a FastAPI-first workflow: keep your schemas, reuse your middleware, and surface endpoints to agents without rewriting controllers. The project is active, with examples and a dedicated site that shows getting started, security, and transport options. -
13
uweb browser: unlimited power
minimal suckless android web browser with unlimited power
... - Customizable: user-defined menus, (new) buttons and gestures for user agents, bookmarklets, url services, shell commands, internal functionality links and text processing etc. - Convenient: book/dictionary/txt/command line/app can be search engine. - Tiny: less than 200k - Fast: run fast, even with thousands of user provided css/scripts - Efficient: less touches, one click to reach any number of search engines without repeated input; automate online services. - URL bar command line support ("!" and .js files as commands). - user-defined site-specific JS/CSS/HTML/preprocessing. - Online play/preview/preprocess for downloadable resources... -
14
ConvNeXt V2
Code release for ConvNeXt V2 model
ConvNeXt V2 is an evolution of the ConvNeXt architecture that co-designs convolutional networks alongside self-supervised learning. The V2 version introduces a fully convolutional masked autoencoder (FCMAE) framework where parts of the image are masked and the network reconstructs the missing content, marrying convolutional inductive bias with powerful pretraining. A key innovation is a new Global Response Normalization (GRN) layer added to the ConvNeXt backbone, which enhances feature... -
15
Bullet Physics SDK
Real-time collision detection and multi-physics simulation for VR
This is the official C++ source code repository of the Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc. We are developing a new differentiable simulator for robotics learning, called Tiny Differentiable Simulator, or TDS. The simulator allows for hybrid simulation with neural networks. It allows different automatic differentiation backends, for forward and reverse mode gradients. TDS can be trained using Deep Reinforcement Learning, or using Gradient based optimization (for example LFBGS). In addition, the simulator can be entirely run on CUDA for fast rollouts, in combination with Augmented Random Search. ... -
16
MTBook
Machine Translation: Foundations and Models
...Its content is compiled into a book, which can be used for the study of senior undergraduates and graduate students in computer and artificial intelligence related majors, and can also be used as reference material for researchers related to natural language processing, especially machine translation. This book is written in tex, and all source codes are open. This book is divided into four parts, each of which consists of several chapters. The order of the chapters refers to the time context of the development of machine translation technology, while taking into account the internal logic of the machine translation knowledge system. -
17
hebrew-gpt_neo
Hebrew text generation models based on EleutherAI's gpt-neo
Hebrew text generation models based on EleutherAI's gpt-neo. Each was trained on a TPUv3-8 which was made available to me via the TPU Research Cloud Program. The Open Super-large Crawled ALMAnaCH coRpus is a huge multilingual corpus obtained by language classification and filtering of the Common Crawl corpus using the goclassy architecture. -
18
Tiny
Tiny Face Detector, CVPR 2017
This repository implements the Tiny Face Detector (from Hu & Ramanan, CVPR 2017) in MATLAB (using MatConvNet). The method is designed to detect tiny faces (i.e. very small-scale faces) by combining multi-scale context modeling, foveal descriptors, and scale enumeration strategies. It provides training/testing scripts, a demo (tiny_face_detector.m), model loading, evaluation on WIDER FACE, and supporting utilities (e.g. cnn_widerface_eval.m). -
19
NASH OS
Nash Operating System for Modern Ecommerce
The all-built-in-one, automatic, ready-to-go out-of-box, easy-to-use state-of-the-art, and really awesome NASH OS! Over 25,000+ flexible features and controls and all scalable!! The most powerful solution ever built to instantly deliver new heights of online ecommerce enterprise to you. -
20
annyang!
Speech recognition for your site
annyang is a tiny javascript library that lets your visitors control your site with voice commands. annyang supports multiple languages, has no dependencies, weighs just 2kb and is free to use. annyang understands commands with named variables, splats, and optional words. Use named variables for one word arguments in your command. Use splats to capture multi-word text at the end of your command (greedy). -
21
AI learning
AiLearning, data analysis plus machine learning practice
...We are also exploring other categories of open source solutions and protocols. I hope you will understand this initiative, combine this initiative with your own interests, and do what you can. Everyone's tiny contributions, together, are the entire open source ecosystem. We are iBooker, a large open-source community, we-media, and online earning community, with a QQ group of more than 10,000 people and at least 10,000 subscribers. The number of Github Stars exceeds 60k, and it ranks in the top 100 of all Github organizations. The daily up of all its websites exceeds 4k, and the peak of Alexa ranking is 20k. ... -
22
tiny-dnn
header only, dependency-free deep learning framework in C++14
tiny-dnn is a C++14 implementation of deep learning. It is suitable for deep learning on limited computational resources, embedded systems, and IoT devices. -
23
CSSgram
CSS library for Instagram filters
Simply put, CSSgram is a library for editing your images with Instagram-like filters directly using CSS. What we're doing is adding filters to the images, as well as applying color and/or gradient overlays via various blending techniques to mimic filter effects. This means less manual image processing and more fun filter effects on the web! We are using pseudo-elements (i.e. :before and :after) to create the filter effects, so you must apply these filters on a containing element (i.e. not a... -
24
smartblob
tiny code, html webcam game or plug brain in each blob, java server
...The gameplay is better experienced in 0.2 which is controlled with the mouse so you dont have enough freedom of movement compared to webcam. This small file contains its own source code including occamserver, a tiny general java server I built which I'll adjust to allow http streaming connections to stay open for faster ajax than a new web call each time. The reshaping and bouncing physics is by springs. -
25
Identification
A tiny "guess what I'm thinking about" game, or an identifier.
This is a tiny game : think about something and answer the questions the software asks. The goal is to have a "identifier" which is able, for instance, to find which mushroom you have in your hands.
