😷 The Fill-Mask Association Test (FMAT): Measuring Propositions in Natural Language.

Brand new TTS solution

A high-performance inference system for large language models, designed for production environments.

A Simple PoC (Proof of Concept) of Hate speech (Toxic comment) Detector API Server

A high-throughput and memory-efficient inference and serving engine for LLMs

A framework for the comparative training and evaluation of statistical and deep learning models for multi-feature categorical sequence modeling, utilizing feature fusion and automated with MLflow and Optuna integration.

This repository is a paper digest of Transformer-related approaches in visual tracking tasks.

Build high-performance AI models with modular building blocks

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

Code I used for my YouTube videos

Popular Large Language Models from scratch - 2024

OpenMMLab Detection Toolbox and Benchmark

vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs

Deep neural network models implemented from scratch in PyTorch for time series forecasting

Large Language Model Text Generation Inference

Code for ICASSP 2024 paper WhisperSeg: Positive Transfer of the Whisper Speech Transformer to Human and Animal Voice Activity Detection

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

🔧 A Kotlin coroutine wrapper around Media3's Transformer API.

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).