Search Results for "transformers" - Page 4
Sort By:
Showing 173 open source projects for "transformers"
View related business solutions-
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.
-
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
1
xFormers
Hackable and optimized Transformers building blocks
xformers is a modular, performance-oriented library of transformer building blocks, designed to allow researchers and engineers to compose, experiment, and optimize transformer architectures more flexibly than monolithic frameworks. It abstracts components like attention layers, feedforward modules, normalization, and positional encoding, so you can mix and match or swap optimized kernels easily. One of its key goals is efficient attention: it supports dense, sparse, low-rank, and... -
2
Mergo
Mergo: merging Go structs and maps since 2013
...Also a lovely comune (municipality) in the Province of Ancona in the Italian region of Marche. Keep in mind that in 0.3.2, Mergo changed Merge()and Map() signatures to support transformers. I added an optional/variadic argument so that it won't break the existing code. You can only merge same-type structs with exported fields initialized as zero value of their type and same-types maps. Mergo won't merge unexported (private) fields but will do recursively any exported one. It won't merge empty structs value as they are zero values too. -
3
GLM-4
GLM-4 series: Open Multilingual Multimodal Chat LMs
GLM-4 is a family of open models from ZhipuAI that spans base, chat, and reasoning variants at both 32B and 9B scales, with long-context support and practical local-deployment options. The GLM-4-32B-0414 models are trained on ~15T high-quality data (including substantial synthetic reasoning data), then post-trained with preference alignment, rejection sampling, and reinforcement learning to improve instruction following, coding, function calling, and agent-style behaviors. The... -
4
txtai
Build AI-powered semantic search applications
txtai executes machine-learning workflows to transform data and build AI-powered semantic search applications. Traditional search systems use keywords to find data. Semantic search applications have an understanding of natural language and identify results that have the same meaning, not necessarily the same keywords. Backed by state-of-the-art machine learning models, data is transformed into vector representations for search (also known as embeddings). Innovation is happening at a rapid... -
AI-generated apps that pass security reviewRetool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.
-
5
Qwen3-Omni
Qwen3-omni is a natively end-to-end, omni-modal LLM
Qwen3-Omni is a natively end-to-end multilingual omni-modal foundation model that processes text, images, audio, and video and delivers real-time streaming responses in text and natural speech. It uses a Thinker-Talker architecture with a Mixture-of-Experts (MoE) design, early text-first pretraining, and mixed multimodal training to support strong performance across all modalities without sacrificing text or image quality. The model supports 119 text languages, 19 speech input languages, and... -
6
LLaMA-Mesh
Unifying 3D Mesh Generation with Language Models
LLaMA-Mesh is a research framework that extends large language models so they can understand and generate 3D mesh data alongside text. The system introduces a method for representing 3D meshes in a textual format by encoding vertex coordinates and face definitions as sequences that can be processed by a language model. By serializing 3D geometry into text tokens, the approach allows existing transformer architectures to generate and interpret 3D models without requiring specialized visual... -
7
IQuest-Coder-V1 Model Family
New family of code large language models (LLMs)
IQuest-Coder-V1 is a cutting-edge family of open-source large language models specifically engineered for code generation, deep code understanding, and autonomous software engineering tasks. These models range from tens of billions to smaller footprints and are trained on a novel code-flow multi-stage paradigm that captures how real software evolves over time — not just static code snapshots — giving them a deeper semantic understanding of programming logic. They support native long contexts... -
8
ESPnet
End-to-end speech processing toolkit
ESPnet is a comprehensive end-to-end speech processing toolkit covering a wide spectrum of tasks, including automatic speech recognition (ASR), text-to-speech (TTS), speech translation (ST), speech enhancement, speaker diarization, and spoken language understanding. It uses PyTorch as its deep learning engine and adopts a Kaldi-style data processing pipeline for features, data formats, and experimental recipes. This combination allows researchers to leverage modern neural architectures while... -
9
Perception Models
State-of-the-art Image & Video CLIP, Multimodal Large Language Models
Perception Models is a state-of-the-art framework developed by Facebook Research for advanced image and video perception tasks. It introduces two primary components: the Perception Encoder (PE) for visual feature extraction and the Perception Language Model (PLM) for multimodal decoding and reasoning. The PE module is a family of vision encoders designed to excel in image and video understanding, surpassing models like SigLIP2, InternVideo2, and DINOv2 across multiple benchmarks. Meanwhile,... -
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.
-
10
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. -
11
Seldon Core
An MLOps framework to package, deploy, monitor and manage models
...Built on Kubernetes, runs on any cloud and on-premises. Framework agnostic, supports top ML libraries, toolkits and languages. Advanced deployments with experiments, ensembles and transformers. Our open-source framework makes it easier and faster to deploy your machine learning models and experiments at scale on Kubernetes. The Kubeflow project is dedicated to making deployments of machine learning (ML) workflows on Kubernetes. -
12
Apiato
PHP Framework for building scalable API's on top of Laravel
The open-source flawless framework for building scalable and testable API-Centric Apps with PHP and Laravel. Authentication with OAuth2.0 for first/third-party clients (using Laravel Passport). Role-Based Access Control (RBAC), seeded with a Super Admin, Roles, and Permissions. Query Parameters support (orderBy, sorted, and filter) with full-text search. Useful Endpoints for managing users, roles/permissions, tokens, and more. API Documentations generator, to generate API docs from PHP... -
13
InfiniteYou
Flexible Photo Recrafting While Preserving Your Identity
InfiniteYou is an open-source image-generation and “identity-preserving image editing / generation” framework from ByteDance, designed to generate high-fidelity images that preserve a subject’s identity while allowing flexible editing or re-creation according to textual prompts. 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. ... -
14
AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis
AutoGPTQ is an implementation of GPTQ (Quantized GPT) that optimizes large language models (LLMs) for faster inference by reducing their computational footprint while maintaining accuracy. -
15
Recurrent Interface Network (RIN)
Implementation of Recurrent Interface Network (RIN)
Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in Pytorch. The author unawaredly reinvented the induced set-attention block from the set transformers paper. They also combine this with the self-conditioning technique from the Bit Diffusion paper, specifically for the latents. The last ingredient seems to be a new noise function based around the sigmoid, which the author claims is better than cosine scheduler for larger images. The big surprise is that the generations can reach this level of fidelity. ... -
16
Deep Learning Models
A collection of various deep learning architectures, models, and tips
...The code favors readability and pedagogy: components are organized so you can trace data flow through layers, losses, optimizers, and evaluation. Examples span fundamental architectures—MLPs, CNNs, RNN/Transformers—and practical tasks like image classification or text modeling. Reproducible training scripts and configuration files make it straightforward to rerun experiments or adapt them to your own datasets. The repo often pairs implementations with notes on design choices and trade-offs, turning it into both a toolbox and a learning resource. ... -
17
Transformers4Rec
Transformers4Rec is a flexible and efficient library
...The library works as a bridge between natural language processing (NLP) and recommender systems (RecSys) by integrating with one of the most popular NLP frameworks, Hugging Face Transformers (HF). Transformers4Rec makes state-of-the-art transformer architectures available for RecSys researchers and industry practitioners. Traditional recommendation algorithms usually ignore the temporal dynamics and the sequence of interactions when trying to model user behavior. Generally, the next user interaction is related to the sequence of the user's previous choices. ... -
18
DeepSeek MoE
Towards Ultimate Expert Specialization in Mixture-of-Experts Language
...The repo publishes both Base and Chat variants of the 16B MoE model (deepseek-moe-16b) and provides evaluation results across benchmarks. It also includes a quick start with inference instructions (using Hugging Face Transformers) and guidance on fine-tuning (DeepSpeed, hyperparameters, quantization). The licensing is MIT for code, with a “Model License” applied to the models. -
19
DocWire SDK
Award-winning modern data processing SDK in C++20
DocWire SDK, a standout C++20AI driven data processing tool, has received award from SourceForge and strong backing from Microsoft. It handles nearly 100 file types, empowering efficient text extraction, web data extraction, and document analysis. For businesses, the shift to DocWire SDK signifies a leap forward. It promises comprehensive document format support and the ability to extract valuable insights from email boxes, databases, and websites using cutting-edge AI. DocWire SDK aims to... -
20
Primus
An abstraction layer for real-time to prevent module lock-in
Primus, the creator god of transformers but now also known as universal wrapper for real-time frameworks. There are a lot of real-time frameworks available for Node.js and they all have different opinions on how real-time should be done. Primus provides a common low level interface to communicate in real-time using various real-time frameworks. Effortless switching between real-time frameworks by changing one single line of code. -
21
CogView
Text-to-Image generation. The repo for NeurIPS 2021 paper
CogView is a large-scale pretrained text-to-image transformer model, introduced in the NeurIPS 2021 paper CogView: Mastering Text-to-Image Generation via Transformers. With 4 billion parameters, it was one of the earliest transformer-based models to successfully generate high-quality images from natural language descriptions in Chinese, with partial support for English via translation. The model incorporates innovations such as PB-relax and Sandwich-LN to enable stable training of very deep transformers without NaN loss issues. ... -
22
ReplitLM
Inference code and configs for the ReplitLM model family
ReplitLM is a family of open-source language models developed by Replit for assisting with programming tasks such as code generation and completion. The project includes model checkpoints, configuration files, and example code that enable developers to run and experiment with the models locally or within machine learning frameworks. These models are designed specifically for coding workflows and are trained on large datasets of source code covering many programming languages and development... -
23
FXtransformer Designer is a graphical design aid for both power and RF transformers. RF Design: Broadband, Single-Tuned, Double-Tuned.
-
24
DiT (Diffusion Transformers)
Official PyTorch Implementation of "Scalable Diffusion Models"
DiT (Diffusion Transformer) is a powerful architecture that applies transformer-based modeling directly to diffusion generative processes for high-quality image synthesis. Unlike CNN-based diffusion models, DiT represents the diffusion process in the latent space and processes image tokens through transformer blocks with learned positional encodings, offering scalability and superior sample quality. The model architecture parallels large language models but for image tokens—each block... -
25
Basaran
Basaran, an open-source alternative to the OpenAI text completion API
Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models. The open source community will eventually witness the Stable Diffusion moment for large language models (LLMs), and Basaran allows you to replace OpenAI's service with the latest open-source model to power your application without modifying a single line of code. Stream generation using various decoding strategies. ...
