Transformer
Showing 36 of 38 projects
A model-definition framework for state-of-the-art machine learning models across text, vision, audio, and multimodal tasks.
A model-definition framework for state-of-the-art machine learning models across text, vision, audio, and multimodal tasks.
A high-throughput, memory-efficient inference and serving engine for large language models (LLMs).
A collection of 60+ annotated PyTorch implementations of deep learning papers with side-by-side explanatory notes.
A high-performance C/C++ port of OpenAI's Whisper model for efficient, cross-platform speech recognition.
High-performance C/C++ port of OpenAI's Whisper for efficient, cross-platform speech recognition.
TensorFlow implementation and pre-trained models for BERT, a bidirectional Transformer for language understanding.
A high-performance serving framework for large language models and multimodal models, delivering low-latency and high-throughput inference.
A fast, memory-efficient reimplementation of OpenAI's Whisper speech-to-text model using CTranslate2.
An end-to-end deep learning library focused on clear code, speed, and research, built by Google Brain.
An end-to-end deep learning library focused on clear code and speed, used for research and production by Google Brain.
A Jest transformer with source map support for testing TypeScript projects.
A domain-specific generative language model pre-trained on biomedical literature for text generation and mining tasks.
A Python library offering scalable and user-friendly implementations of state-of-the-art neural forecasting models.
A collection of transformer protein language models for predicting structure, function, and designing proteins from sequences.
A curated collection of research papers and resources on Vision Transformers (ViT) for computer vision tasks.
A Rust-native port of Hugging Face Transformers providing ready-to-use NLP pipelines and transformer models like BERT, GPT2, and T5.
A multimodal protein language model for generative protein design and engineering by jointly reasoning over sequence, structure, and function.
A JAX/Flax-based framework for easy and scalable pre-training, fine-tuning, evaluation, and serving of large language models.
Import SVG files in React Native projects the same way you would in a web application.
An open-source study on neural question generation using transformers, providing simplified training and inference pipelines.
A PyTorch framework for training neural learning-to-rank models with flexible loss functions and scoring architectures.
A PyTorch framework for efficient 3D semantic and panoptic segmentation using superpoint-based transformer architectures.
A Laravel package for building API responses using Fractal transformers with elegant Laravel-style abstractions.
A collection of transformer-based foundation models for genomics and transcriptomics, enabling tasks like sequence analysis, functional prediction, and conversational DNA exploration.
A foundation model for multi-species genome understanding, achieving state-of-the-art performance on 28 genomic tasks.
A Google Colab notebook that transcribes YouTube videos using OpenAI's Whisper speech recognition model.
A joint audio tagging and speech recognition model that adds audio event detection to OpenAI Whisper with minimal computational overhead.
A BERT-based foundation model pretrained on large-scale scRNA-seq data for automated cell type annotation in single-cell analysis.
A web tool that visually formats text and generates Swift/Objective-C code for attributed strings.
A bi-directional equivariant transformer for long-range DNA sequence modeling, enabling reverse-complement aware genomic analysis.
A vision transformer architecture that aggregates nested local transformers on image blocks for better accuracy, data efficiency, and convergence.
A pure Crystal machine learning library for building and training neural networks with CPU/GPU support and PyTorch compatibility.
A T5-based model for bidirectional translation between molecular structures (SMILES) and natural language descriptions.
A FlashAttention 2 implementation for JAX with block-wise document mask optimization and context parallelism for efficient long-sequence training.
A deep learning model using transformer architecture to predict compound-protein interactions from molecular and protein sequences.
Related Tags
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.