Search Results for "transformers"
Sort By:
73 projects for "transformers" with 1 filter applied:
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
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
spacy-transformers
Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy
...These techniques can be used to import knowledge from raw text into your pipeline, so that your models are able to generalize better from your annotated examples. You can convert word vectors from popular tools like FastText and Gensim, or you can load in any pre trained transformer model if you install spacy-transformers. You can also do your own language model pretraining via the spacy pre train command. You can even share your transformer or another contextual embedding model across multiple components, which can make long pipelines several times more efficient. To use transfer learning, you’ll need at least a few annotated examples for what you’re trying to predict. -
2
Transformers in Time Series
A professionally curated list of awesome resources
...It compiles literature from major conferences and journals and categorizes them by application domains such as forecasting, anomaly detection, and classification. The repository also provides a taxonomy that helps researchers understand different architectural variations of transformers designed for time series data. These models are particularly important because transformers can capture long-range dependencies in sequential data, which makes them well suited for complex temporal patterns in real-world datasets. -
3
DINOv3
Reference PyTorch implementation and models for DINOv3
...DINOv3 removes the need for complex augmentations or momentum encoders, streamlining the pipeline while maintaining or improving feature quality. The model supports multiple backbone architectures, including Vision Transformers (ViT), and can handle larger image resolutions with improved stability during training. The learned embeddings generalize robustly across tasks like classification, retrieval, and segmentation without fine-tuning, showing state-of-the-art transfer performance among self-supervised models. -
4
GeoAI
GeoAI: Artificial Intelligence for Geospatial Data
GeoAI is a comprehensive open-source Python package designed to integrate artificial intelligence techniques with geospatial data analysis, enabling users to perform advanced geographic modeling and visualization tasks with ease. It provides a unified framework that combines machine learning libraries such as PyTorch and Transformers with geospatial tools, allowing users to process satellite imagery, aerial photos, and vector datasets in a streamlined workflow. The platform supports a wide range of tasks including image classification, object detection, segmentation, and change detection, making it suitable for applications in environmental monitoring, urban planning, and disaster response. ... -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
5
SwanLab
An open-source, modern-design AI training tracking and visualization
...SwanLab supports both cloud and self-hosted deployments, allowing organizations to run the system privately or integrate it into shared development environments. The platform integrates with a wide range of machine learning frameworks including PyTorch, Transformers, Keras, and other widely used training ecosystems. -
6
DeiT (Data-efficient Image Transformers)
Official DeiT repository
DeiT (Data-efficient Image Transformers) shows that Vision Transformers can be trained competitively on ImageNet-1k without external data by using strong training recipes and knowledge distillation. Its key idea is a specialized distillation strategy—including a learnable “distillation token”—that lets a transformer learn effectively from a CNN or transformer teacher on modest-scale datasets. -
7
Torch Pruning
DepGraph: Towards Any Structural Pruning
...It introduces a graph-based algorithm called DepGraph that automatically identifies dependencies between layers, allowing parameters to be pruned safely across complex architectures. This dependency analysis makes it possible to prune large networks such as transformers, convolutional networks, and diffusion models without breaking the computational graph. Torch-Pruning physically removes parameters rather than masking them, which results in smaller and faster models during both training and inference. The toolkit supports a wide variety of architectures used in computer vision and large language models, making it a flexible solution for model compression tasks. -
8
DFlash
Block Diffusion for Ultra-Fast Speculative Decoding
...The project includes support for multiple draft models, example integration code, and scripts to benchmark performance, and it is structured to work with popular model serving stacks like SGLang and the Hugging Face Transformers ecosystem. -
9
Attention Residuals (AttnRes)
Drop-in replacement for standard residual connections in Transformers
Attention Residuals is a research-driven architectural innovation for transformer-based models that replaces traditional residual connections with an attention-based mechanism to improve information flow across layers. In standard transformers, residual connections simply sum outputs from previous layers, which can lead to uncontrolled growth of hidden states and dilution of early-layer information in deep networks. Attention Residuals introduces a learnable softmax attention mechanism that allows each layer to selectively retrieve and weight useful representations from earlier layers, making depth dynamically adaptive rather than uniformly aggregated. ... -
8 Monitoring Tools in One APM. Install in 5 Minutes.AppSignal works out of the box for Ruby, Elixir, Node.js, Python, and more. 30-day free trial, no credit card required.
-
10
AI Engineering Transition Path
Research papers and blogs to transition to AI Engineering
AI Engineering Resources is an open educational repository that compiles research papers, tutorials, and learning materials for software engineers transitioning into artificial intelligence engineering roles. The project organizes resources that cover fundamental topics required to understand modern AI systems, including transformers, vector embeddings, tokenization, infrastructure design, and mixture-of-experts architectures. Instead of presenting isolated tutorials, the repository provides a structured pathway that guides engineers through the technical knowledge needed to build and deploy large language model systems. The materials include curated research papers, blog posts, and code examples that explain both theoretical foundations and practical implementation strategies. ... -
11
AiLearning-Theory-Applying
Quickly get started with AI theory and practical applications
...The project also introduces important concepts such as probability theory, linear algebra, regression models, clustering methods, and neural network architectures. Advanced sections explore modern AI topics including transformers, BERT-based natural language processing systems, and practical competition-style machine learning workflows. -
12
PydanticAI
Agent Framework / shim to use Pydantic with LLMs
...PydanticAI is a Python Agent Framework designed to make it less painful to build production-grade applications with Generative AI. Built by the team behind Pydantic (the validation layer of the OpenAI SDK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor, and many more). -
13
OuteTTS
Interface for OuteTTS models
...It provides a high-level Interface API that wraps model configuration, speaker handling, and audio generation so you can focus on integrating speech into your application rather than wiring up low-level engines. The project supports multiple backends including llama.cpp (Python bindings and server), Hugging Face Transformers, ExLlamaV2, VLLM and a JavaScript interface via Transformers.js, allowing it to run on CPUs, NVIDIA CUDA GPUs, AMD ROCm, Vulkan-capable GPUs, and Apple Metal. It also includes a notion of speaker profiles: you can create a speaker from a short audio sample, save it as JSON, and reuse it for consistent voice identity across generations and sessions. ... -
14
Vitest
Next generation testing framework powered by Vite
Next-generation testing framework powered by Vite. Reuse Vite's config and plugins - consistent across your app and tests. But Vitest is not required. Expect, snapshot, coverage, and more - migrating from Jest is straightforward. Out-of-box ESM, TypeScript and JSX support powered by esbuild. -
15
Babel
The compiler for writing next generation JavaScript
Babel is a toolchain that helps you write code in the latest version of JavaScript. It converts ECMAScript 2015+ code into a backwards compatible version of JavaScript that can be run by older JavaScript engines. With Babel you can transform syntax, polyfill features that are missing in your target environment, transform source code and more! -
16
Scalaz
Principled Functional Programming in Scala
Scalaz is a foundational functional-programming library for Scala that provides type classes, data types, and syntax to write pure, composable code. It implements classic abstractions such as Functor, Applicative, Monad, Monoid, Foldable, and Traverse, along with powerful transformers (ReaderT, StateT, WriterT, OptionT, and more) to structure effects. The library offers rich data structures—\/ (disjunction), Validation, NonEmptyList, IList, and Free—that help model errors, invariants, and interpretable programs. Its type class–oriented design lets you write generic algorithms over capabilities rather than concrete types, improving reuse and testability. ... -
17
GLM-OCR
Accurate × Fast × Comprehensive
GLM-OCR is an open-source multimodal optical character recognition (OCR) model built on a GLM-V encoder–decoder foundation that brings robust, accurate document understanding to complex real-world layouts and modalities. Designed to handle text recognition, table parsing, formula extraction, and general information retrieval from documents containing mixed content, GLM-OCR excels across major benchmarks while remaining highly efficient with a relatively compact parameter size (~0.9B),... -
18
DeepSeek-OCR 2
Visual Causal Flow
...The repository provides model code and inference scripts that let researchers and developers run and benchmark the system on both images and PDFs, with support for batch evaluation and optimized pipelines leveraging vLLM and transformers. -
19
VoxCPM
TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
...Instead of converting speech into discrete tokens, it uses an end-to-end diffusion-autoregressive architecture built on the MiniCPM-4 backbone, combining hierarchical language modeling, finite scalar quantization (FSQ), and local Diffusion Transformers. This design helps decouple semantic and acoustic information while preserving fine-grained prosody, leading to more stable and expressive generation than many discrete-token systems. Trained on a large 1.8-million-hour bilingual corpus, VoxCPM can infer appropriate speaking style from context, dynamically adjusting intonation, rhythm, and emotional tone. ... -
20
Backtrack Sampler
An easy-to-understand framework for LLM samplers
Backtrack Sampler is a framework designed for experimenting with custom sampling strategies for language models (LLMs), enabling the ability to rewind and revise generated tokens. It allows developers to create and test their own token generation strategies by providing a base structure for manipulating logits and probabilities, making it a flexible tool for those interested in fine-tuning the behavior of LLMs. -
21
ChatGLM-6B
ChatGLM-6B: An Open Bilingual Dialogue Language Model
ChatGLM-6B is an open bilingual (Chinese + English) conversational language model based on the GLM architecture, with approximately 6.2 billion parameters. The project provides inference code, demos (command line, web, API), quantization support for lower memory deployment, and tools for finetuning (e.g., via P-Tuning v2). It is optimized for dialogue and question answering with a balance between performance and deployability in consumer hardware settings. Support for quantized inference... -
22
Vision Transformer Pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA
...Because it stays close to vanilla PyTorch, you can integrate custom datasets and training loops without framework lock-in. It’s widely used as an educational reference for people learning transformers in vision and as a lightweight baseline for research prototypes. The project encourages experimentation—swap optimizers, change augmentations, or plug the transformer backbone into downstream tasks. -
23
HunyuanImage-3.0
A Powerful Native Multimodal Model for Image Generation
...The GitHub repo includes code, scripts, model loading instructions, inference utilities, prompt handling, and integration with standard ML tooling (e.g. Hugging Face / Transformers). -
24
RxDart
The Reactive Extensions for Dart
...The library aims to stay idiomatic with Dart Streams while giving developers the ergonomic power long associated with the ReactiveX family. In practice, it encourages clear separation between data producers, transformers, and consumers. -
25
Super comprehensive deep learning notes
Super Comprehensive Deep Learning Notes
...The repository contains hundreds of Jupyter notebooks that are richly annotated and organized by topic, progressing from basic Python and PyTorch fundamentals to advanced neural network designs like ResNet, transformers, and object detection algorithms. It’s not just a dry code repository; it includes theoretical explanations alongside hands-on examples, loss function explorations, optimization routines, and full end-to-end experiments on real datasets, making it highly suitable for both self-study and classroom use.
