Search Results for "transformer"
Sort By:
140 projects for "transformer" with 2 filters applied:
-
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.
-
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
Vision Transformer Pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA
...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. -
2
Megatron
Ongoing research training transformer models at scale
Megatron is a large, powerful transformer developed by the Applied Deep Learning Research team at NVIDIA. This repository is for ongoing research on training large transformer language models at scale. We developed efficient, model-parallel (tensor, sequence, and pipeline), and multi-node pre-training of transformer based models such as GPT, BERT, and T5 using mixed precision. -
3
MiniMax H3
MiniMax H3 is a general-purpose, omni-modal generative system
...Ref2VA accepts multiple reference images, videos, and audio clips for more controlled results. Its architecture uses a unified multimodal sequence and a 33-billion-parameter H3-Omni-Transformer that jointly predicts video and audio latents. The repository also provides model components, inference code, prompt guidance, and specialized generation skills. -
4
OpenMythos
A theoretical reconstruction of the Claude Mythos architecture
OpenMythos is an experimental, open-source implementation that attempts to reconstruct a hypothesized architecture behind advanced language models using a design called a Recurrent-Depth Transformer. The project explores the idea that instead of stacking hundreds of unique transformer layers, a smaller set of layers can be reused iteratively during inference to achieve deeper reasoning without increasing parameter count. It divides computation into three main stages, including a pre-processing phase, a looped recurrent reasoning block, and a final output refinement stage, creating a structured pipeline for inference. ... -
$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.
-
5
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. ... -
6
RF-DETR
RF-DETR is a real-time object detection and segmentation
RF-DETR is an open-source computer vision framework that implements a real-time object detection and instance segmentation model based on transformer architectures. Developed by Roboflow, the project builds upon modern vision transformer backbones such as DINOv2 to achieve strong accuracy while maintaining efficient inference speeds suitable for real-time applications. The model is designed to detect objects and segment them within images or video streams using a unified detection pipeline. ... -
7
MoBA
MoBA: Mixture of Block Attention for Long-Context LLMs
...The approach allows language models to scale to significantly longer input contexts without the quadratic computational cost normally associated with transformer attention mechanisms. -
8
Transformers & LLMs cheatsheet
VIP cheatsheet for Stanford's CME 295 Transformers and Large Language
Transformers & LLMs cheatsheet is an educational repository focused on transformers, large language models, and modern generative AI architectures based on Stanford CME 295 coursework. The project compiles structured notes, mathematical explanations, diagrams, and implementation references covering transformer internals, attention mechanisms, tokenization, training pipelines, and inference strategies. It is designed to help students and practitioners understand the technical foundations behind contemporary AI systems such as GPT-style models and multimodal architectures. The repository emphasizes conceptual clarity while still addressing practical engineering considerations involved in training and scaling transformer models. ... -
9
Z-Image
Image generation model with single-stream diffusion transformer
Z-Image is an efficient, open-source image generation foundation model built to make high-quality image synthesis more accessible. With just 6 billion parameters — far fewer than many large-scale models — it uses a novel “single-stream diffusion Transformer” architecture to deliver photorealistic image generation, demonstrating that excellence does not always require extremely large model sizes. The project includes several variants: Z-Image-Turbo, a distilled version optimized for speed and low resource consumption; Z-Image-Base, the full-capacity foundation model; and Z-Image-Edit, fine-tuned for image editing tasks. ... -
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
Janus
Unified Multimodal Understanding and Generation Models
...By splitting those pathways but keeping one unified core transformer, Janus maintains flexibility and achieves strong performance across tasks previously requiring distinct architectures. The repository includes pretrained checkpoints (for example 1.3B and 7B parameter versions), a Gradio demo, and guidance for local deployment. -
11
model2Vec
Fast State-of-the-Art Static Embeddings
...The resulting models can be used for a wide range of tasks, including semantic search, clustering, classification, and retrieval-augmented generation systems. One of its key advantages is its simplicity, as it requires minimal dependencies and can generate embeddings extremely quickly compared to traditional transformer-based approaches. -
12
SageAttention
NeurIPS2025 Spotlight] Quantized Attention
SageAttention is an open-source optimization library designed to accelerate the attention mechanism used in transformer-based neural networks. Since attention operations are often the most computationally expensive component of modern AI models, SageAttention introduces quantization techniques that significantly reduce computational overhead while preserving model accuracy. The system achieves this by using low-precision numerical formats such as INT4, FP8, or INT8 to represent key matrices within the attention computation. ... -
13
rust-bert
Rust native ready-to-use NLP pipelines and transformer-based models
rust-bert is a Rust-based implementation of transformer-based natural language processing models that provides ready-to-use pipelines for tasks such as text classification, summarization, and question answering. The project ports many capabilities of the Hugging Face Transformers ecosystem into the Rust programming language. It allows developers to run state-of-the-art NLP models like BERT, GPT-2, and DistilBERT directly within Rust applications while maintaining high performance and memory efficiency. ... -
14
HunyuanDiT
Diffusion Transformer with Fine-Grained Chinese Understanding
HunyuanDiT is a high-capability text-to-image diffusion transformer with bilingual (Chinese/English) understanding and multi-turn dialogue capability. It trains a diffusion model in latent space using a transformer backbone and integrates a Multimodal Large Language Model (MLLM) to refine captions and support conversational image generation. It supports adapters like ControlNet, IP-Adapter, LoRA, and can run under constrained VRAM via distillation versions. -
15
VOID
Video Object and Interaction Deletion
...Unlike traditional inpainting methods that only erase pixels or simple artifacts, VOID models the full interaction dynamics between objects and their environment, including shadows, reflections, and even physical consequences such as movement or balance changes. Built on top of transformer-based architectures and fine-tuned for video inpainting tasks, the system uses interaction-aware mask conditioning to ensure temporal consistency across frames. One of its most notable capabilities is its ability to simulate realistic scene behavior after object removal, such as causing an object to fall naturally if its support is removed, which significantly enhances realism. -
16
Train LLM From Scratch
A straightforward method for training your LLM
Train LLM From Scratch is an educational PyTorch project that shows how to build and train a transformer-based language model from the ground up. It is based on the architecture described in Attention Is All You Need and is designed to make the training pipeline understandable rather than hidden behind a large framework. The repository walks through the process from downloading data to generating text with a trained model. It supports training smaller or larger models, including million- and billion-parameter configurations depending on available hardware. ... -
17
Whisper
Robust Speech Recognition via Large-Scale Weak Supervision
...It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification. A Transformer sequence-to-sequence model is trained on various speech processing tasks, including multilingual speech recognition, speech translation, spoken language identification, and voice activity detection. These tasks are jointly represented as a sequence of tokens to be predicted by the decoder, allowing a single model to replace many stages of a traditional speech-processing pipeline. ... -
18
VGGT
[CVPR 2025 Best Paper Award] VGGT
VGGT is a transformer-based framework aimed at unifying classic visual geometry tasks—such as depth estimation, camera pose recovery, point tracking, and correspondence—under a single model. Rather than training separate networks per task, it shares an encoder and leverages geometric heads/decoders to infer structure and motion from images or short clips. -
19
HunyuanVideo-Avatar
Tencent Hunyuan Multimodal diffusion transformer (MM-DiT) model
HunyuanVideo-Avatar is a multimodal diffusion transformer (MM-DiT) model by Tencent Hunyuan for animating static avatar images into dynamic, emotion-controllable, and multi-character dialogue videos, conditioned on audio. It addresses challenges of motion realism, identity consistency, and emotional alignment. Innovations include a character image injection module, an Audio Emotion Module for transferring emotion cues, and a Face-Aware Audio Adapter to isolate audio effects on faces, enabling multiple characters to be animated in a scene. ... -
20
TabPFN
Foundation Model for Tabular Data
TabPFN is an open-source machine learning system that introduces a foundation model designed specifically for tabular data analysis. The model is based on transformer architectures and implements a prior-data fitted network that can perform supervised learning tasks such as classification and regression with minimal configuration. Unlike many traditional machine learning workflows that require extensive hyperparameter tuning and training cycles, TabPFN is pre-trained to perform inference directly on tabular datasets. ... -
21
AirLLM
AirLLM 70B inference with single 4GB GPU
...This layer-wise inference approach allows models with tens of billions of parameters to run on devices with only a few gigabytes of VRAM. AirLLM preprocesses model weights so that each transformer layer can be loaded independently during computation, reducing the memory footprint while still performing full inference. As a result, developers can experiment with models that previously required specialized high-end GPUs. -
22
HunyuanVideo-Foley
Multimodal Diffusion with Representation Alignment
...The model architecture aligns audio, video, and text representations to produce realistic synchronized soundtracks. Produces high-quality 48 kHz audio output suitable for professional use. Hybrid architecture combining multimodal transformer blocks and unimodal refinement blocks. Temporal alignment via frame-level synchronization modules (e.g. Synchformer). -
23
Advanced AI explainability for PyTorch
Advanced AI Explainability for computer vision
...The project implements Grad-CAM and several related visualization methods that highlight the regions of an image that most strongly influence a neural network’s decision. These visualization techniques allow developers and researchers to better understand how convolutional neural networks and transformer-based vision models make predictions. The library supports a wide variety of tasks including image classification, object detection, semantic segmentation, and similarity analysis. It also provides metrics and evaluation tools that help measure the reliability and quality of the generated explanations. By integrating easily with PyTorch models, the library allows developers to diagnose model errors, detect biases in datasets, and improve model transparency. -
24
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. -
25
ML Retreat
Machine Learning Journal for Intermediate to Advanced Topics
...Rather than functioning as a traditional tutorial series, the repository is organized as a learning journey that progressively explores increasingly advanced subjects. Topics include large language models, graph neural networks, mechanistic interpretability, transformer architectures, and emerging research areas such as quantum machine learning. The repository includes references to influential research papers, lectures, and educational content from well-known machine learning educators.
