Search Results for "alignment" - Page 4
Sort By:
Showing 125 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.
-
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
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... -
2
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... -
3
ChatGLM2-6B
ChatGLM2-6B: An Open Bilingual Chat LLM
ChatGLM2-6B is the second-gen Chinese-English conversational LLM from ZhipuAI/Tsinghua. It upgrades the base model with GLM’s hybrid pretraining objective, 1.4 TB bilingual data, and preference alignment—delivering big gains on MMLU, CEval, GSM8K, and BBH. The context window extends up to 32K (FlashAttention), and Multi-Query Attention improves speed and memory use. The repo includes Python APIs, CLI & web demos, OpenAI-style/FASTAPI servers, and quantized checkpoints for lightweight local deployment on GPUs or CPU/MPS. -
4
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. ... -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
5
GLM-4-32B-0414
Open Multilingual Multimodal Chat LMs
...The model is pre-trained on 15 trillion tokens of high-quality data, including substantial synthetic reasoning datasets, and further enhanced with reinforcement learning and human preference alignment for improved instruction-following and function calling. Variants like GLM-Z1-32B-0414 offer deep reasoning and advanced mathematical problem-solving, while GLM-Z1-Rumination-32B-0414 specializes in long-form, complex research-style writing using scaled reinforcement learning and external search tools. Despite its large capacity, the model supports user-friendly local deployment and efficient fine-tuning with available scripts. -
6
SoniTranslate
Synchronized Translation for Videos
SoniTranslate is a video translation and dubbing system that produces synchronized target-language audio tracks for existing video content. It provides a web UI built with Gradio, allowing users to upload a video, choose source and target languages, and then run a pipeline that handles transcription, translation and re-synthesis of speech. Under the hood, it uses advanced speech and diarization models to separate speakers, align audio with timecodes and respect subtitle timing, which lets... -
7
aictx
Repo-local continuity runtime for AI coding agents. Helps them continu
AICTX helps Codex, Claude, GitHub Copilot and other coding agents continue work across sessions by preserving the last useful execution state: active work, next actions, decisions, failures, validation evidence and repo context. The continuity idea is not to add more hidden memory or dump more context into the prompt. AICTX keeps operational continuity inside the repo: - active Work State and next action; - execution summaries and handoffs; - explicit decisions; - known failures and... -
8
Safety-Prompts
Chinese safety prompts for evaluating and improving the safety of LLMs
...The prompts are structured to test whether models generate outputs that align with human values and safety guidelines when faced with potentially harmful or sensitive requests. Researchers and developers use the dataset to benchmark how well models avoid unsafe responses and follow alignment constraints. The repository also serves as a training resource for improving model alignment by providing examples of prompts that require safe reasoning and appropriate refusal behavior. In addition to evaluation prompts, the project references related tools and benchmarks for assessing model safety across different contexts. -
9
Bert-VITS2
VITS2 backbone with multilingual-bert
...It provides emotional modeling through “emo embeddings,” allowing voices to be conditioned on different affective states during synthesis. Releases include optimizations for Japanese and English alignment, expanded training data, spec caching and pre-generation tools, as well as ONNX export for more lightweight inference deployments. -
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
Style Aligned
Official code for Style Aligned Image Generation via Shared Attention
...Instead of fully re-generating an image—and risking changes to lighting, texture, or rendering choices—the method aligns internal features across denoising steps so the target edit inherits the source style. This alignment acts like a constraint on the model’s evolution, steering composition, palette, and brushwork even as objects or attributes change. The result is more consistent edits across a set, which is crucial for workflows like product variations, character sheets, or brand-coherent art. The repository provides reproducible scripts, reference prompts, and guidance for tuning strengths so users can dial in subtle retouches or bolder substitutions. ... -
11
LLMDataHub
Quick guide (especially) for trending instruction finetuning dataset
...Each dataset entry typically includes information such as size, language coverage, intended use cases, and links to the original data sources. The repository focuses particularly on datasets useful for chatbot training, instruction-following tasks, and alignment training scenarios. By organizing these resources into a curated hub, the project helps researchers and developers identify the most relevant training corpora for building conversational AI systems. The repository also highlights datasets suitable for reinforcement learning from human feedback and other alignment strategies used in modern language model training. -
12
InternLM
Official release of InternLM series
InternLM is an open-source family of multilingual foundation and chat models, accompanied by an ecosystem that supports training, inference, and application development. The repository highlights multiple model sizes intended to serve different needs, from efficient research and prototyping to more capable deployments for complex scenarios. Beyond model weights, the project emphasizes an ecosystem view, pointing developers to compatible tools and projects across training and inference so... -
13
CSAw - NLP for low-resource languages
CSAw is an NLP framework for low-resource languages
...See the preprint article here: https://arxiv.org/abs/1807.02226 The current framework includes transduction algorithms (i.e., from text to semantic representation and back again) and some components needed for automatic language model building (lexical alignment and grammar rule generation). Recently, we have added transliteration functionality. The project is currently incomplete. More to come. -
14
State of Open Source AI
Clarity in the current fast-paced mess of Open Source innovation
...Because the AI domain moves quickly, part of the aim is to make the content maintainable and updateable by the community. The structure includes chapters or sections about model formats, evaluation benchmarks, hardware/backends, MLOps systems, alignment and safety issues, and open datasets. The repository contains the text (in Markdown or similar), configuration for build or publishing (static site or e-book), and contributor guidelines. -
15
ChatGPT DAN
ChatGPT DAN, Jailbreaks prompt
...It highlights both the capabilities and limitations of large language models when exposed to unconventional instructions. The project reflects ongoing experimentation within the AI community around control, alignment, and creative use of generative systems. -
16
OpenNMT-tf
Neural machine translation and sequence learning using TensorFlow
...For example, the following instance defines a sequence-to-sequence model with 2 concatenated input features, a self-attentional encoder, and an attentional RNN decoder sharing its input and output embeddings. Sequence to sequence models can be trained with guided alignment and alignment information are returned as part of the translation API. -
17
OptiMate
Libraries for optimizing AI models, inference speed, and GPU usage
Optimate is an open source collection of libraries designed to optimize the performance and cost efficiency of artificial intelligence models across different stages of the machine learning lifecycle. It groups several internal optimization tools developed by Nebuly AI into a single repository that focuses on improving inference speed, reducing infrastructure usage, and streamlining model training workflows. Its modules help developers automatically apply optimization techniques that better... -
18
CPT
CPT: A Pre-Trained Unbalanced Transformer
...Position Embeddings We extend the max_position_embeddings from 512 to 1024. We initialize the new version of models with the old version of checkpoints with vocabulary alignment. Token embeddings found in the old checkpoints are copied. And other newly added parameters are randomly initialized. We further train the new CPT & Chinese BART 50K steps with batch size 2048, max-seq-length 1024, peak learning rate 2e-5, and warmup ratio 0.1. Aiming to unify both NLU and NLG tasks, We propose a novel Chinese Pre-trained Un-balanced Transformer (CPT). -
19
MTCNN Face Detection Alignment
Joint Face Detection and Alignment
MTCNN_face_detection_alignment is an implementation of the “Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks” algorithm. The algorithm uses a cascade of three convolutional networks (P-Net, R-Net, O-Net) to jointly detect faces (bounding boxes) and align facial landmarks in a coarse-to-fine manner, leveraging multi-task learning. Non-maximum suppression and bounding box regression at each stage. -
20
GLIDE (Text2Im)
GLIDE: a diffusion-based text-conditional image synthesis model
...The repository provides both model code and pretrained checkpoints, making it possible for researchers and developers to experiment with text-to-image synthesis. GLIDE includes advanced techniques such as classifier-free guidance, which improves the quality and alignment of generated images with the input text. The project also offers sampling scripts and utilities for exploring how diffusion models can be applied to multimodal tasks. As one of the early diffusion-based text-to-image systems, glide-text2im laid important groundwork for later advances in generative AI research. -
21
Following Instructions with Feedback
Training Language Models to Follow Instructions with Human Feedback
The following-instructions-human-feedback repository contains the code and supplementary materials underpinning OpenAI’s work in training language models (InstructGPT models) that better follow user instructions through human feedback. The repo hosts the model card, sample automatic evaluation outputs, and labeling guidelines used in the process. It is explicitly tied to the “Training language models to follow instructions with human feedback” paper, and serves as a reference for how OpenAI... -
22
CLIP Guided Diffusion
A CLI tool/python module for generating images from text
...Non-square Generations (experimental) Generate portrait or landscape images by specifying a number to offset the width and/or height. Uses fewer timesteps over the same diffusion schedule. Sacrifices accuracy/alignment for quicker runtime. options: - 25, 50, 150, 250, 500, 1000, ddim25,ddim50,ddim150, ddim250,ddim500,ddim1000 (default: 1000) Prepending a number with ddim will use the ddim scheduler. e.g. ddim25 will use the 25 timstep ddim scheduler. This method may be better at shorter timestep_respacing values. Multiple prompts can be specified with the | character. ... -
23
VITS
Conditional Variational Autoencoder with Adversarial Learning
...The repository provides training and inference pipelines for common datasets such as LJ Speech (single-speaker) and VCTK (multi-speaker), including filelists, configs, and preprocessing scripts. It also includes monotonic alignment search code and g2p preprocessing, which are crucial components for aligning text and speech in an end-to-end setup. -
24
Transformer TTS
Implementation of a Transformer based neural network
...It takes inspiration from architectures like FastSpeech, FastSpeech 2, FastPitch, and Transformer TTS, and extends them with its own aligner and forward models. The system separates alignment learning and acoustic modeling: an autoregressive Transformer is used as an aligner to extract phoneme-to-frame durations, while a non-autoregressive “ForwardTransformer” generates mel-spectrograms conditioned on text and durations. This design addresses common autoregressive issues such as repetition, skipped words, and unstable attention, and results in robust, fast synthesis where all frames are predicted in parallel. ... -
25
TNN
Uniform deep learning inference framework for mobile
TNN, a high-performance, lightweight neural network inference framework open sourced by Tencent Youtu Lab. It also has many outstanding advantages such as cross-platform, high performance, model compression, and code tailoring. The TNN framework further strengthens the support and performance optimization of mobile devices on the basis of the original Rapidnet and ncnn frameworks. At the same time, it refers to the high performance and good scalability characteristics of the industry's...
