Search Results for "alignment" - Page 5
Sort By:
Showing 492 open source projects for "alignment"
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.
-
$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
tinypdf
Minimal PDF creation library
tinypdf is a minimal, zero-dependency PDF generation library that focuses on the core “put content on a page” use case while intentionally skipping heavyweight features. It is designed to be extremely small and approachable, making it a good fit when you want to generate real PDFs in Node/TypeScript without pulling in a large toolkit. The library supports essential primitives like writing text, drawing basic shapes, and placing JPEG images, which covers common needs such as invoices,... -
2
txiki.js
A tiny JavaScript runtime
txiki.js is a lightweight and modern JavaScript runtime designed to provide a compact yet powerful alternative to larger runtimes like Node.js and Deno. It is built on top of QuickJS-ng as its JavaScript engine and uses libuv for asynchronous I/O and system-level operations, allowing it to support a wide range of platform capabilities. The runtime aims to implement modern ECMAScript standards while aligning with WinterCG specifications, making it suitable for both server-side and scripting... -
3
SimpleHTR
Handwritten Text Recognition (HTR) system implemented with TensorFlow
SimpleHTR is an open-source implementation of a handwriting text recognition system based on deep learning techniques. The project focuses on converting images of handwritten text into machine-readable digital text using neural networks. The system uses a combination of convolutional neural networks and recurrent neural networks to extract visual features and model sequential character patterns in handwriting. It also employs connectionist temporal classification (CTC) to align predicted... -
4
Telos
Telos is an open-sourced framework for creating Deep Context
...The project emphasises creating deep context about matters that humans care about, making underlying intentions explicit rather than implicit. It is structured so that you can document your purpose, link it to your strategies and metrics, and thereby maintain clarity and alignment over time. Although lightweight in implementation (for example a .md context file), its ambition is philosophical: helping actors live intentionally and track progress toward purpose. It aligns with broader themes of human flourishing and human-centred frameworks that Miessler discusses in his writing. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
HunyuanWorld-Voyager
RGBD video generation model conditioned on camera input
HunyuanWorld-Voyager is a next-generation video diffusion framework developed by Tencent-Hunyuan for generating world-consistent 3D scene videos from a single input image. By leveraging user-defined camera paths, it enables immersive scene exploration and supports controllable video synthesis with high realism. The system jointly produces aligned RGB and depth video sequences, making it directly applicable to 3D reconstruction tasks. At its core, Voyager integrates a world-consistent video... -
6
CUTLASS
CUDA Templates for Linear Algebra Subroutines
CUTLASS is a collection of CUDA C++ template abstractions for implementing high-performance matrix-multiplication (GEMM) and related computations at all levels and scales within CUDA. It incorporates strategies for hierarchical decomposition and data movement similar to those used to implement cuBLAS and cuDNN. CUTLASS decomposes these "moving parts" into reusable, modular software components abstracted by C++ template classes. These thread-wide, warp-wide, block-wide, and device-wide... -
7
AIGCPanel
One-stop AI digital human system with video voice synthesis tools
AIGCPanel is an open source desktop application designed as a comprehensive, all-in-one platform for creating AI-powered digital humans and media content. It integrates multiple capabilities such as video synthesis, voice synthesis, and voice cloning into a unified interface, allowing users to generate realistic audiovisual outputs with minimal setup. AIGCPanel focuses heavily on simplifying the management of local AI models by providing streamlined workflows for importing, configuring, and... -
8
Talk to Figma MCP
AI bridge enabling Cursor agents to read and modify Figma designs
cursor-talk-to-figma-mcp is an open source integration that connects AI coding agents with Figma through the Model Context Protocol (MCP). It allows AI tools such as Cursor or other compatible agents to directly communicate with Figma documents and interact with design elements programmatically. Through this integration, an AI assistant can read the structure of a design, retrieve information about nodes or selections, and perform modifications to the layout or content.... -
9
LongWriter
Unleashing 10,000+ Word Generation from Long Context LLMs
LongWriter is an open-source framework and set of large language models designed to enable ultra-long text generation that can exceed 10,000 words while maintaining coherence and structure. Traditional large language models can process large inputs but often struggle to generate long outputs due to limitations in training data and alignment strategies. LongWriter addresses this challenge by introducing a specialized dataset and training approach that encourages models to produce longer responses. The system uses an agent-based pipeline called AgentWrite that decomposes large writing tasks into smaller subtasks, allowing the model to produce long documents section by section. ... -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
10
nanochat
The best ChatGPT that $100 can buy
...The repository stitches together every stage of the lifecycle: tokenizer training, pretraining a Transformer on a large web corpus, mid-training on dialogue and multiple-choice tasks, supervised fine-tuning, optional reinforcement learning for alignment, and finally efficient inference with caching. Its north star is approachability and speed: you can boot a fresh GPU box and drive the whole pipeline via a single script, producing a usable chat model in hours and a clear markdown report of what happened. The code is written to be read—concise training loops, transparent configs, and minimal wrappers—so you can audit each step, tweak it, and rerun without getting lost in framework indirection. -
11
Multimodal
TorchMultimodal is a PyTorch library
This project, also known as TorchMultimodal, is a PyTorch library for building, training, and experimenting with multimodal, multi-task models at scale. The library provides modular building blocks such as encoders, fusion modules, loss functions, and transformations that support combining modalities (vision, text, audio, etc.) in unified architectures. It includes a collection of ready model classes—like ALBEF, CLIP, BLIP-2, COCA, FLAVA, MDETR, and Omnivore—that serve as reference... -
12
ImageBind
ImageBind One Embedding Space to Bind Them All
ImageBind is a multimodal embedding framework that learns a shared representation space across six modalities—images, text, audio, depth, thermal, and IMU (inertial motion) data—without requiring explicit pairwise training for every modality combination. Instead of aligning each pair independently, ImageBind uses image data as the central binding modality, aligning all other modalities to it so they can interoperate zero-shot. This creates a unified embedding space where representations from... -
13
Profile Data
Analyze computation-communication overlap in V3/R1
...The repository contains JSON trace files like train.json, prefill.json, decode.json, and associated assets. Users can load them into tools like Chrome tracing to inspect GPU idle times, overlapping operations, and scheduling alignment. The idea is to bring transparency to internal efficiency tradeoffs, enabling researchers to reproduce, analyze, or improve on DeepSeek’s parallelism strategies. The README explains how trace data corresponds to forward/backward chunks, settings (e.g. EP64, TP1, 4K sequence length), and notes that pipeline communication is excluded for simplicity. -
14
HunyuanVideo-Avatar
Tencent Hunyuan Multimodal diffusion transformer (MM-DiT) model
HunyuanVideo-Avatar is a multimodal diffusion transformer (MM-DiT) model by Tencent Hunyuan for animating static avatar images into dynamic, emotion-controllable, and multi-character dialogue videos, conditioned on audio. It addresses challenges of motion realism, identity consistency, and emotional alignment. Innovations include a character image injection module, an Audio Emotion Module for transferring emotion cues, and a Face-Aware Audio Adapter to isolate audio effects on faces, enabling multiple characters to be animated in a scene. Character image injection module for better consistency between training and inference conditioning. ... -
15
Cpp17
Chinese translation of C++17 The Complete Guide
...The content is organized into multiple parts: basic language features (e.g. structured binding, inline variables, enhanced switch, lambdas), template and compile-time features (e.g. fold expressions, class template argument deduction, constexpr improvements), and the additions to the standard library (e.g. std::optional, std::variant, std::string_view, file system, concurrency, and parallel algorithms). It also covers enhancements to existing STL components, new library utilities, and advanced topics like polymorphic memory resources (PMR), alignment, and generic programming improvements. -
16
Super Tiny Icons
Super Tiny Icons are miniscule SVG versions of your favourite website
...Designers and developers can embed the icons directly, recolor them via CSS, or combine them in sprites without raster assets. The repository maintains consistent viewboxes and alignment so icons sit neatly alongside text and other UI elements. It is especially useful for landing pages, status banners, and mobile experiences where every byte matters. -
17
DreamO
A Unified Framework for Image Customization
DreamO is a unified, open-source framework from ByteDance for advanced image customization and generation that consolidates multiple “image manipulation” tasks into a single system, rather than requiring separate specialized models. Built on a diffusion-transformer (DiT) backbone, it supports a diverse set of tasks — including identity preservation, virtual “try-on” (e.g. clothing, accessories), style transfer, IP adaptation (objects/characters), and layout/condition-aware customizations —... -
18
Zerocopy
Zerocopy makes zero-cost memory manipulation effortless
...It also includes marker traits like KnownLayout, Immutable, and Unaligned to define type characteristics used in conversions. Complementing these traits are conversion macros that perform compile-time checks to ensure size and alignment safety, providing zero runtime overhead for unconditional casts. -
19
Enterprise-Scale
The Azure Landing Zones (Enterprise-Scale) architecture
Enterprise-Scale is a reference architecture and set of landing-zone blueprints for building large, governed Azure estates. It codifies recommended patterns—network topology, identity integration, subscription and resource organization, policy assignment, and guardrails—so enterprises can provision repeatable, secure, and compliant environments for workloads. The project supplies deployable artifacts (Bicep/ARM/Terraform modules, examples, and documentation) to accelerate consistent... -
20
WebMCP
Enabling web apps to get accessed by AI agents
WebMCP is a proposed web standard that enables web applications to expose their functionality as JavaScript-based “tools” accessible to AI agents, browser assistants, and assistive technologies. It allows developers to define structured, natural-language-described functions directly in client-side code, effectively turning web pages into Model Context Protocol (MCP)-like servers running in the browser. Unlike backend integrations, WebMCP executes tools within the live web page, preserving... -
21
IoTDB
Apache IoTDB
Apache IoTDB (Database for Internet of Things) is an IoT native database with high performance for data management and analysis, deployable on the edge and the cloud. Due to its light-weight architecture, high performance and rich feature set together with its deep integration with Apache Hadoop, Spark and Flink, Apache IoTDB can meet the requirements of massive data storage, high-speed data ingestion and complex data analysis in the IoT industrial fields. In the scene of factories, there... -
22
PFAAT is a Java-based multiple sequence alignment editor and viewer designed for protein family analysis. You can download PFAAT from http://pfaat.sourceforge.net/
-
23
Matcha-TTS
A fast TTS architecture with conditional flow matching
Matcha-TTS is a non-autoregressive neural text-to-speech architecture that uses conditional flow matching to generate speech quickly while maintaining natural quality. It models speech as an ODE-based generative process, and conditional flow matching lets it reach high-quality audio in only a few synthesis steps, which greatly reduces latency compared to score-matching diffusion approaches. The model is fully probabilistic, so it can generate diverse realizations of the same text while still... -
24
PKU Beaver
Constrained Value Alignment via Safe Reinforcement Learning
PKU Beaver is an open-source research project focused on improving the safety alignment of large language models through reinforcement learning from human feedback under explicit safety constraints. The framework introduces techniques that separate helpfulness and harmlessness signals during training, allowing models to optimize for useful responses while minimizing harmful behavior. To support this process, the project provides datasets containing human-labeled examples that encode both performance preferences and safety constraints across multiple dimensions. ... -
25
MView
Extract and reformat a sequence database search or multiple alignment
NOTE: The MView repository and web pages have moved to: https://github.com/desmid/mview https://desmid.github.io/mview/ Release tarballs will continue to be uploaded to SourceForge. ---- MView is a command line utility that extracts and reformats the results of a sequence database search or a multiple alignment, optionally adding HTML markup for web page layout. It can also be used as a filter to extract and convert searches or alignments to common formats. Inputs: - Sequence database search: BLAST, FASTA suites. - Multiple sequence alignment: CLUSTAL, HSSP, MSF, FASTA, PIR, MAF. Outputs: - HTML, FASTA, CLUSTAL, MSF, PIR, RDB (tab-separated). ...
