Search Results for "16"
Sort By:
Showing 21 open source projects for "16"
View related business solutions-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
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.
-
1
CTranslate2
Fast inference engine for Transformer models
...The execution is significantly faster and requires less resources than general-purpose deep learning frameworks on supported models and tasks thanks to many advanced optimizations: layer fusion, padding removal, batch reordering, in-place operations, caching mechanism, etc. The model serialization and computation support weights with reduced precision: 16-bit floating points (FP16), 16-bit integers (INT16), and 8-bit integers (INT8). The project supports x86-64 and AArch64/ARM64 processors and integrates multiple backends that are optimized for these platforms: Intel MKL, oneDNN, OpenBLAS, Ruy, and Apple Accelerate. -
2
Open Notebook
An Open Source implementation of Notebook LM with more flexibility
Open Notebook is an open-source, privacy-focused alternative to Google’s Notebook LM that gives users full control over their research and AI workflows. Designed to be self-hosted, it ensures complete data sovereignty by keeping your content local or within your own infrastructure. The platform supports 16+ AI providers—including OpenAI, Anthropic, Ollama, Google, and LM Studio—allowing flexible model choice and cost optimization. Open Notebook enables users to organize and analyze multi-modal content such as PDFs, videos, audio files, web pages, and Office documents. It combines full-text and vector search with context-aware AI chat to deliver insights grounded in your own research materials. ... -
3
Ian Xiaohei Illustrations
Chinese Little Black Weird Text Illustration Generation Skill
...It is centered on the “Xiaohei” visual character and turns abstract ideas, judgments, metaphors, and workflows into clear editorial images. The skill is not a generic illustration prompt pack, because it gives AI agents a specific visual system to follow. Its default style uses a 16:9 white-background composition with rough hand-drawn lines and small red, orange, or blue annotation marks. It is especially useful for knowledge creators who want recognizable article visuals without designing from scratch. The project works as a reusable creative instruction layer for AI-assisted content production. -
4
LingBot-World
Advancing Open-source World Models
...LingBot-World supports long-term temporal consistency, maintaining coherent scenes and interactions over minute-level horizons. With real-time interactivity and sub-second latency at 16 FPS, it is well-suited for interactive applications and rapid experimentation. The project is fully open-access, releasing both code and models to help bridge the gap between closed and open world-model systems. LingBot-World empowers researchers and developers in areas such as content creation, gaming, robotics, and embodied AI learning. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
5
AI YouTube Shorts Generator
A python tool that uses GPT-4, FFmpeg, and OpenCV
...It analyzes input video (whether a local file or a YouTube URL), transcribes audio (with optional GPU-accelerated speech-to-text), uses an AI model to identify the most compelling or engaging segments, and then crops/resizes the video and applies subtitle overlays, producing a polished short video without manual editing. The tool streamlines multiple steps of the tedious short-form video workflow: highlight detection, clipping, subtitle generation, cropping to vertical 9:16 format, and final rendering — reducing hours of editing to a mostly automated pipeline. Because it supports both local and online video sources, it's flexible whether you're working with your own recorded content or repurposing existing longer-form videos. -
6
Surya
Implementation of the Surya Foundation Model for Heliophysics
...It is designed to forecast solar phenomena—such as flares, solar wind, irradiance, and active region behavior—by predicting future solar images with a sophisticated long–short vision transformer architecture, thereby enabling improved space weather forecasting. Foresees solar flares, wind, EUV spectra, and active region formation in advance. Achieves approximately 16% improvement in forecasting accuracy over traditional methods. 366-million‑parameter foundation model capturing general-purpose solar representations. -
7
LitGPT
20+ high-performance LLMs with recipes to pretrain, finetune at scale
LitGPT is a collection of over 20 high-performance large language models (LLMs) accompanied by recipes to pretrain, finetune, and deploy them at scale. It provides implementations without abstractions, making it beginner-friendly while offering advanced features like flash attention and support for various precision levels. LitGPT is designed to run efficiently across multiple GPUs or TPUs, catering to both small-scale and large-scale deployments. -
8
clone-voice
A sound cloning tool with a web interface, using your voice
Clone-voice is a local voice-cloning tool that lets you synthesize speech in any target voice or convert one recording into another voice using the same timbre. It is built around Coqui’s XTTS-v2 model, so it inherits multilingual support and modern neural TTS quality while wrapping it in a user-friendly desktop workflow. The app is designed to be very easy to use: you download a precompiled package, double-click app.exe, and it launches a browser-based web interface where you control... -
9
Z-Image
Image generation model with single-stream diffusion transformer
Z-Image is an efficient, open-source image generation foundation model built to make high-quality image synthesis more accessible. With just 6 billion parameters — far fewer than many large-scale models — it uses a novel “single-stream diffusion Transformer” architecture to deliver photorealistic image generation, demonstrating that excellence does not always require extremely large model sizes. The project includes several variants: Z-Image-Turbo, a distilled version optimized for speed and... -
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
10
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. -
11
LLM TLDR
95% token savings. 155x faster queries. 16 languages
LLM TLDR is a tool that leverages large language models (LLMs) to generate concise, coherent summaries (TL;DRs) of long documents, articles, or text files, helping users quickly understand large amounts of content without reading every word. It integrates with LLM APIs to handle input texts of varying lengths and complexity, applying techniques like chunking, context management, and multi-pass summarization to preserve accuracy even when the source is very large. The system supports both... -
12
Learn Claude Code
Bash is all you need, write a claude code with only 16 line code
Learn Claude Code is an educational repository that teaches how modern AI coding agents work by walking learners through a sequence of progressively more complex agent implementations, starting with a minimal Bash-based agent and culminating in agents with explicit planning, subagents, and skills. It emphasizes a hands-on learning path where each version (from v0 to v4) adds conceptual building blocks like the core agent loop, todo planning, task decomposition, and domain knowledge skills,... -
13
BitNet
BitNet: Scaling 1-bit Transformers for Large Language Models
...In this approach, neural network weights are quantized to approximately one bit per parameter, allowing models to operate with far lower memory usage than traditional 16-bit or 32-bit neural networks. The architecture introduces specialized layers such as BitLinear, which replace standard linear projections in transformer networks with quantized operations. By limiting weight precision while maintaining efficient scaling and normalization strategies, the architecture aims to retain competitive performance while significantly reducing hardware requirements. -
14
MyBox
Easy Tools of PDF, Image, File, Network, Data, and Medias
javafx-desktop-apps pdf image ocr icc barcode color-palette text bytes markdown html archive compress digest video audio editor converter media https://github.com/Mararsh/MyBox Self-contain packages need not java env nor installation. Jar packages need Java 16 or higher. -
15
DALL-E in Pytorch
Implementation / replication of DALL-E, OpenAI's Text to Image
...Currently only the VAE with a codebook size of 1024 is offered, with the hope that it may train a little faster than OpenAI's, which has a size of 8192. In contrast to OpenAI's VAE, it also has an extra layer of downsampling, so the image sequence length is 256 instead of 1024 (this will lead to a 16 reduction in training costs, when you do the math). -
16
Procgen
Procedurally-Generated Game-Like Gym-Environments
Procgen (short for Procedural Generation Benchmark) is a suite of 16 procedurally generated, game-like reinforcement learning environments designed to evaluate generalization and sample efficiency in RL agents. Unlike fixed, deterministic environments, Procgen generates new levels (layouts, obstacles, visual variation) each episode, making it impossible for an agent to simply memorize trajectories. -
17
FARM
Fast & easy transfer learning for NLP
...With FARM you can build fast proofs-of-concept for tasks like text classification, NER or question answering and transfer them easily into production. Easy fine-tuning of language models to your task and domain language. AMP optimizers (~35% faster) and parallel preprocessing (16 CPU cores => ~16x faster). Modular design of language models and prediction heads. Switch between heads or combine them for multitask learning. Full Compatibility with HuggingFace Transformers' models and model hub. Smooth upgrading to newer language models. Integration of custom datasets via Processor class. Powerful experiment tracking & execution. -
18
Exposure
Learning infinite-resolution image processing with GAN and RL
...ACM Transactions on Graphics (presented at SIGGRAPH 2018) Exposure is originally designed for RAW photos, which assumes 12+ bit color depth and linear "RGB" color space (or whatever we get after demosaicing). jpg and png images typically have only 8-bit color depth (except 16-bit pngs) and the lack of information (dynamic range/activation resolution) may lead to suboptimal results such as posterization. Moreover, jpg and most pngs assume an sRGB color space, which contains a roughly 1/2.2 Gamma correction, making the data distribution different from training images (which are linear). Exposure is just a prototype (proof-of-concept) of our latest research, and there are definitely a lot of engineering efforts required to make it suitable for a real product. -
19
SuRankCo
Supervised Ranking of Contigs in de novo Assemblies
...For more details about SuRankCo and its functioning, please see "SuRankCo: Supervised Ranking of Contigs in de novo Assemblies" Mathias Kuhring, Piotr Wojtek Dabrowski, Andreas Nitsche and Bernhard Y. Renard (http://www.biomedcentral.com/1471-2105/16/240/abstract) PLEASE NOTE, it is recommended to read the paper and the readme.txt file before using SuRankCo. Update Jun2015: * Minor changes to enable BAM support. Update Feb2014: * Added support for FASTA/SAM assemblies in addition to ACE/FASTQ(QUAL). NOTE: features of FASTA/SAM assemblies do not include BaseCount, BaseSeqmentCount and ContigQualities yet. -
20
Ministral 3 3B Reasoning 2512
Compact 3B-param multimodal model for efficient on-device reasoning
...This reasoning-tuned variant is optimized for tasks like math, coding, and other STEM-related problem solving, making it suitable for applications that require logical reasoning, analysis, or structured thinking. Despite its modest size, the model is designed for edge deployment and can run locally, fitting in ~16 GB of VRAM in BF16 or under 8 GB of RAM/VRAM when quantized. It supports dozens of languages, allowing it to function across global and multilingual contexts. The model retains strong system-prompt adherence, supports function-calling with structured JSON output, and offers a large 256k token context window for extended context reasoning. -
21
DiffusionGemma
NVFP4 DiffusionGemma model for fast multimodal text generation
...The model supports a 256K-token context window, configurable thinking mode, native function calling, structured JSON output, and multilingual inference across 35+ languages. The NVFP4 quantization reduces weights and activations from 16-bit to 4-bit, lowering disk size and GPU memory needs for vLLM deployment.
- Previous
- You're on page 1
- Next