Search Results for "alignment" - Page 3
Sort By:
Showing 522 open source projects for "alignment"
View related business solutions-
$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.
-
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
1
Heretic
Fully automatic censorship removal for language models
Heretic is an open-source Python tool that automatically removes the built-in censorship or “safety alignment” from transformer-based language models so they respond to a broader range of prompts with fewer refusals. It works by applying directional ablation techniques and a parameter optimization strategy to adjust internal model behaviors without expensive post-training or altering the core capabilities. Designed for researchers and advanced users, Heretic makes it possible to study and experiment with uncensored model responses in a reproducible, automated way. ... -
2
VGGT-Ω
[CVPR 2026 Oral] VGGT Omega
...The project is associated with 3D understanding workflows where models infer scene geometry without a traditional multi-stage reconstruction pipeline. It includes pretrained model variants with different resolutions and text-alignment capabilities, though checkpoint access may require approval. The repository also provides a Gradio demo that can visualize predicted cameras and depth-unprojected point clouds as a GLB scene. VGGT-Omega is best suited for researchers and developers working on 3D reconstruction, visual geometry, and image-based scene understanding. -
3
Open3D
A modern library for 3D data processing
Open3D is an open-source library that supports rapid development of software that deals with 3D data. The Open3D frontend exposes a set of carefully selected data structures and algorithms in both C++ and Python. The backend is highly optimized and is set up for parallelization. Open3D was developed from a clean slate with a small and carefully considered set of dependencies. It can be set up on different platforms and compiled from source with minimal effort. The code is clean, consistently... -
4
Karpathy Skills
A single CLAUDE.md file to improve Claude Code behavior
...Its principles encourage the agent to think before coding, prefer simple implementations, make surgical changes, and define verifiable success criteria. It can be installed as a Claude Code plugin or copied directly into a project as reusable instructions. Its main value is not automation, but behavioral alignment that helps coding agents produce cleaner, smaller, and more deliberate changes. -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
5
HeartMuLa
A Family of Open Sourced Music Foundation Models
HeartMuLa is the open-source library and reference implementation for the HeartMuLa family of music foundation models, designed to support both music generation and music-related understanding tasks in a cohesive stack. At the center is HeartMuLa, a music language model that generates music conditioned on inputs like lyrics and tags, with multilingual support that broadens the range of lyric-driven use cases. The project also includes HeartCodec, a music codec optimized for high... -
6
MeshLab
The open source mesh processing system
MeshLab is an open-source, portable, and extensible system for the processing and editing of unstructured large 3D triangular meshes. It is aimed to help the processing of the typical not-so-small unstructured models arising in 3D scanning, providing a set of tools for editing, cleaning, healing, inspecting, rendering and converting this kind of meshes. MeshLab is mostly based on the open source C++ mesh processing library VCGlib developed at the Visual Computing Lab of ISTI - CNR. VCG can... -
7
SWIFT LLM
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs
SWIFT LLM is a comprehensive framework developed within the ModelScope ecosystem for training, fine-tuning, evaluating, and deploying large language models and multimodal models. The platform provides a full machine learning pipeline that supports tasks ranging from model pre-training to reinforcement learning alignment techniques. It integrates with popular inference engines such as vLLM and LMDeploy to accelerate deployment and runtime performance. The framework also includes support for many modern training strategies, including preference learning methods and parameter-efficient fine-tuning techniques. ms-swift is designed to work with hundreds of language and multimodal models, providing a unified environment for experimentation and production deployment. -
8
DOCX
Generate .docx files with JS/TS with a nice declarative API
...You can specify additional properties to the section, by providing a properties attribute. Everything (text, images, graphs etc) in OpenXML is organized in paragraphs. To change the text alignment of a paragraph, add an AlignmentType option on the paragraph.for center, left, right or justified. When a paragraph is justified, you may want to not justify the contents of incomplete lines, which end in a soft line break. Paragraphs have .keepLines() and .keepNext() methods that allow restricting page breaks within and between paragraphs. ... -
9
Node Thermal Printer
Node.js module for thermal printers command line printing
node-thermal-printer is a Node.js library that enables communication with thermal receipt printers using ESC/POS commands. It is designed for point-of-sale (POS) applications, allowing developers to generate receipts, barcodes, QR codes, and formatted text. -
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.
-
10
IHUB Plugins
A set of Gradle plugins that greatly simplify project management
A collection of Gradle plugins designed to simplify project setup, versioning, dependency management, Spring Boot configuration, GraalVM support, and more, tailored for IHub’s monorepos and enterprise workflows. -
11
DOLMA
Data and tools for generating and inspecting OLMo pre-training data
DOLMA (Data Optimization and Learning for Model Alignment) is a framework designed to manage large-scale datasets for training and fine-tuning language models efficiently. -
12
DataChain
AI-data warehouse to enrich, transform and analyze unstructured data
...Datachain can persist features of Python objects returned by AI models, and enables vectorized analytical operations over them. The typical use cases are data curation, LLM analytics and validation, image segmentation, pose detection, and GenAI alignment. Datachain is especially helpful if batch operations can be optimized – for instance, when synchronous API calls can be parallelized or where an LLM API offers batch processing. -
13
kallisto
Near-optimal RNA-Seq quantification
kallisto is a program for near-optimal quantification of transcript abundances from RNA-Seq data, or more generally of target sequences using high-throughput sequencing reads. It is based on the idea of using pseudoalignment to quickly determine reads and targets’ compatibility, with no need for alignment. According to benchmarks done on a Mac desktop computer, kallisto can quantify 30 million human bulk RNA-seq reads in less than 3 minutes with just the read sequences and a transcriptome index, that in itself can take more than 10 minutes to build. And since it uses pseudoalignment, it is robust to errors in the reads and preserves the key information needed for quantification. ... -
14
DeepSeek V2
Strong, Economical, and Efficient Mixture-of-Experts Language Model
...The V2 model is expected to support more advanced features like better context window handling, more efficient inference, better performance on challenging tasks, and stronger alignment with human feedback. Because DeepSeek is pushing open-weight competition, this V2 iteration is meant to solidify its position in benchmark rankings and in developer adoption. The code in the repository may include description files, support for tool use or plug-in architectures, and artifacts showing fine-tuning or prompt templates. -
15
GLM-4.6
Agentic, Reasoning, and Coding (ARC) foundation models
GLM-4.6 is the latest iteration of Zhipu AI’s foundation model, delivering significant advancements over GLM-4.5. It introduces an extended 200K token context window, enabling more sophisticated long-context reasoning and agentic workflows. The model achieves superior coding performance, excelling in benchmarks and practical coding assistants such as Claude Code, Cline, Roo Code, and Kilo Code. Its reasoning capabilities have been strengthened, including improved tool usage during inference... -
16
HivisionIDPhoto
HivisionIDPhotos: a lightweight and efficient AI ID photos tools
HivisionIDPhotos is an open-source AI project designed to automatically generate professional ID photographs from ordinary portrait images. The system uses computer vision and machine learning models to detect faces, segment the subject from the background, and produce standardized identification photos suitable for official documents. It is designed as a lightweight tool that can perform inference offline and run efficiently on CPUs without requiring powerful GPUs. The software analyzes... -
17
Fish Speech
SOTA Open Source TTS
...The repository hosts the code and tooling for training, fine-tuning, and serving high-quality TTS, while the current flagship models (OpenAudio-S1 and S1-mini) are distributed via Fish Audio’s playground and Hugging Face. The models are evaluated with Seed TTS metrics and achieve exceptionally low word and character error rates, indicating strong intelligibility and alignment between text and audio. Fish Speech emphasizes expressive and controllable voices: it supports a long list of emotion tags, tone markers, and special audio effect markers that can be embedded in the text to drive prosody and vocal style, from basic emotions to nuanced states like sarcastic, conciliative, or hysterical. The system is multilingual and cross-lingual, handling multiple languages in a single input without explicit phoneme markup, and is trained on large-scale datasets. -
18
Transcoder
Hardware-accelerated video transcoding using Android MediaCodec APIs
Transcoder by DeepMedia is an AI-powered video-to-video speech translation engine that enables fully automated multilingual dubbing. Unlike traditional speech translation systems that rely on multi-stage pipelines, Transcoder directly translates one speaker’s video into another language while preserving facial expressions, lip-sync, and vocal identity. Designed for real-time use and production-grade pipelines, Transcoder combines advanced deep learning models with GPU acceleration to deliver... -
19
OpenAI Agents JS
A lightweight, powerful framework for multi-agent workflows
openai-agents-js is the JavaScript/TypeScript version of the OpenAI Agents SDK, designed to give developers a lightweight but powerful framework for building agentic workflows, voice agents, and tool-augmented LLM systems in JS/TS environments. The SDK is provider-agnostic, meaning while it’s deeply compatible with OpenAI’s APIs, you can also adapt it to use other backends or extension layers. At its core, it introduces primitives like Agents, Tools, Guardrails, and Handoffs, letting you... -
20
CBIG
Computational Brain Imaging Group tools
CBIG is a comprehensive toolkit maintained by Thomas Yeo’s Computational Brain Imaging Group containing tools for processing and analyzing neuroimaging data—including fMRI preprocessing pipelines, brain parcellation algorithms, mental disorder subtyping models, fMRI dynamic models, registrations between brain spaces, and phenotypic prediction algorithms. After cloning/downloading this repository, please see README inside setup directory to see instructions on how to set up your local... -
21
G0DM0D3
LIBERATED AI CHAT
G0DM0D3 is an experimental AI interaction framework designed to enable unrestricted or “liberated” conversational behavior in language models by altering how prompts and system instructions are structured. It is part of a broader ecosystem of projects that explore the boundaries of AI alignment, control, and prompt engineering. The tool provides a collection of prompt templates and interaction patterns that attempt to override or bypass built-in behavioral constraints in language models. It is primarily used for experimentation, red-teaming, and studying how AI systems respond to unconventional or adversarial inputs. ... -
22
PaLM + RLHF - Pytorch
Implementation of RLHF (Reinforcement Learning with Human Feedback)
PaLM-rlhf-pytorch is a PyTorch implementation of Pathways Language Model (PaLM) with Reinforcement Learning from Human Feedback (RLHF). It is designed for fine-tuning large-scale language models with human preference alignment, similar to OpenAI’s approach for training models like ChatGPT. -
23
CyberPPT
A Codex Skill for generating high-density, editable PowerPoints
...Image-generation blueprints guide reconstruction while native text, shapes, tables, charts, and vectors preserve core editability. Multiple quality gates inspect structure, visuals, overflow, spatial alignment, curves, and editable elements. Delivery includes the PPTX, rendered previews, manifests, and QA results, with failed hard gates blocking completion. -
24
canvas-editor
Canvas-based WYSIWYG rich text editor with advanced layout tools
canvas-editor is a browser-based rich text editor that renders content using HTML5 Canvas and SVG instead of traditional DOM-based approaches. It is designed to provide a WYSIWYG editing experience similar to word processors, enabling precise control over layout, rendering, and document structure. canvas-editor supports a wide range of formatting and document features, including text styling, tables, images, and embedded elements, all managed through a structured data model. Its architecture... -
25
Tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models
tiktoken is a high-performance, tokenizer library (based on byte-pair encoding, BPE) designed for use with OpenAI’s models. It handles encoding and decoding text to token IDs efficiently, with minimal overhead. Because tokenization is a fundamental step in preparing text for models, tiktoken is optimized for speed, memory, and correctness in model contexts (e.g. matching OpenAI’s internal tokenization). The repo supports multiple encodings (e.g. “cl100k_base”) and lets users switch encoding...
