Search Results for "alignment" - Page 2
Sort By:
Showing 131 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.
-
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.
-
1
Tokenizers
Fast State-of-the-Art Tokenizers optimized for Research and Production
...Takes less than 20 seconds to tokenize a GB of text on a server’s CPU. Easy to use, but also extremely versatile. Designed for both research and production. Full alignment tracking. Even with destructive normalization, it’s always possible to get the part of the original sentence that corresponds to any token. Does all the pre-processing: Truncation, Padding, add the special tokens your model needs. -
2
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. ... -
3
PowerPoint-ist
Web presentation editor replicating many PowerPoint features online
...PPTist supports a wide variety of slide elements such as text, images, shapes, charts, tables, audio, video, and mathematical formulas, enabling users to design rich and complex presentations. It also includes tools for slide organization, element alignment, animation, and theme management to streamline presentation design workflows. In addition to editing capabilities, it provides export options for presentation files and other formats, although compatibility with traditional presentation formats. -
4
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... -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
5
face.evoLVe
High-Performance Face Recognition Library on PaddlePaddle & PyTorch
...The project provides a comprehensive framework for building and training modern face recognition models using deep learning architectures. It includes components for face alignment, landmark localization, data preprocessing, and model training pipelines that allow developers to construct end-to-end facial recognition systems. The repository supports multiple neural network backbones such as ResNet, DenseNet, MobileNet, and ShuffleNet, enabling experimentation with different architectures depending on performance requirements. ... -
6
RLHF-Reward-Modeling
Recipes to train reward model for RLHF
...The repository provides training recipes and implementations for building reward and preference models using modern machine learning frameworks. It supports multiple optimization strategies commonly used in alignment pipelines, including reinforcement learning with PPO, iterative supervised fine-tuning using rejection sampling, and direct preference optimization methods. The project also includes evaluation results showing that the trained reward models can achieve competitive performance compared with other open-source alignment systems. -
7
LLM Course
Course to get into Large Language Models (LLMs)
...It emphasizes reproducible experiments: each step is demonstrated with runnable code, clear dependencies, and references to commonly used open-source models and libraries. Learners get exposure to multiple adaptation strategies—LoRA/QLoRA, instruction fine-tuning, and alignment techniques—so they can choose approaches that fit their hardware and budgets. The materials also cover inference optimization and quantization to make serving LLMs feasible on commodity GPUs or even CPUs, which is crucial for side projects and startups. Evaluation is treated as a first-class topic, with examples of automatic and human-in-the-loop methods to catch regressions and verify quality beyond simple loss values. ... -
8
verl
Volcano Engine Reinforcement Learning for LLMs
...The library focuses on scalability and efficiency, offering distributed training loops, mixed precision, and replay/buffering utilities that keep accelerators busy. It ships with reference implementations of popular alignment algorithms and clear examples that make it straightforward to reproduce baselines before customizing. Data pipelines treat human feedback, simulated environments, and synthetic preferences as interchangeable sources, which helps with rapid experimentation. VERL is meant for both research and production hardening: logging, checkpointing, and evaluation suites are built in so you can track learning dynamics and regressions over time. -
9
UCO3D
Uncommon Objects in 3D dataset
...The repository includes automated downloaders with checksum verification, fine-grained controls to fetch only selected modalities or super-categories, and a lightweight Python API for loading frames, geometry, and splats on demand. Metadata is indexed in SQLite for quick queries at scale, and helper builders handle alignment, undistortion, frame extraction from videos, and cropping around the object. -
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
10
Chatterbox
SoTA open-source TTS
Chatterbox is Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. Try it now on our... -
11
Hunyuan3D 2.0
High-Resolution 3D Assets Generation with Large Scale Diffusion Models
The Hunyuan3D-2 model, developed by Tencent, is designed for generating high-resolution 3D assets using large-scale diffusion models. This model offers advanced capabilities for creating detailed 3D models, including texture enhancements, multi-view shape generation, and rapid inference for real-time applications. It is particularly useful for industries requiring high-quality 3D content, such as gaming, film, and virtual reality. Hunyuan3D-2 supports various enhancements and is available... -
12
InfiniteYou
Flexible Photo Recrafting While Preserving Your Identity
...Using an architecture built around diffusion transformers (DiTs), InfiniteYou introduces a component called InfuseNet that injects identity features derived from reference images into the generation process — via residual connections — so that the output matches the person’s identity closely, without sacrificing visual quality or text-image alignment. The team uses a multi-stage training strategy with synthetic multi-sample data per identity to fine-tune for both identity consistency and aesthetic quality. Compared to prior methods, InfiniteYou significantly improves on identity similarity, text-prompt adherence, overall image quality, and avoids common problems such as face copy-pasting artifacts. -
13
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... -
14
YuE
Open source AI model for generating full songs from lyrics prompts
...It focuses on transforming text inputs such as lyrics and genre prompts into complete musical compositions that include both vocal and instrumental tracks. Unlike many shorter audio generators, the model is capable of producing songs that last several minutes while maintaining coherent musical structure and alignment with the provided lyrics. YuE introduces a family of models built on large language model architectures that process music generation as a sequence prediction task. YuE also incorporates techniques such as track-decoupled prediction and progressive conditioning to help manage complex audio signals and maintain consistency throughout long compositions. ... -
15
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... -
16
L1B3RT45
Harmless liberation prompts
...It is positioned more as a prompt experimentation archive than a traditional software library, emphasizing the study of how instruction phrasing can influence AI outputs. The project reflects the growing interest in prompt security, jailbreak testing, and model alignment research within the AI community. Its materials are often used by researchers and enthusiasts studying robustness, safety, and adversarial prompting dynamics. Because of its unconventional focus, it functions primarily as a research and exploration resource rather than a production tool. Overall, L1B3RT4S serves as a niche but widely referenced collection for studying advanced prompt manipulation patterns. -
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
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. -
19
NanoClaw
A lightweight alternative to Clawdbot / OpenClaw
Nanoclaw is a lightweight, security-focused personal agent runtime designed as a slimmer alternative to larger “personal assistant” agent stacks, with an emphasis on being easy to audit and safe by default. It runs agent execution inside Apple containers to provide strong isolation boundaries, so individual chats and actions can be sandboxed with tighter filesystem and process separation than a typical single-process bot. The project connects directly to WhatsApp, letting you deploy an... -
20
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. ... -
21
GLM-Image
GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image
...It excels at generating images that include complex layouts and detailed text content, making it especially useful for posters, diagrams, info-graphics, social media graphics, and visual content that requires precise text placement and semantic alignment. Because it blends linguistic reasoning with image synthesis, GLM-Image produces visual outputs where semantic relationships and textual accuracy are prioritized alongside artistic style and realism, and its model structure enables it to handle dense visual knowledge tasks that challenge many pure diffusion models. The model’s design and weights are available under an open-source license that encourages experimentation, integration, and deployment across a range of creative workflows. -
22
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. -
23
LLMSurvey
A Survey of Large Language Models
...The repository organizes hundreds of research papers into thematic sections that reflect the main areas of LLM research, including model architectures, training strategies, evaluation benchmarks, alignment techniques, and downstream applications. By structuring the literature in a navigable format, LLMSurvey allows researchers and practitioners to quickly explore important publications in the field without manually searching through multiple databases. -
24
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.... -
25
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.
