transformers

The web application for Texo, a minimalist SOTA LaTeX OCR model which contains only 20M parameters runs in browser. | 超轻量SOTA LaTeX公式识别模型，20M参数量的 web 应用仓库

Tool for converting LLMs from uni-directional to bi-directional by removing causal mask for tasks like classification and sentence embeddings. Compatible with 🤗 transformers.

The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.

Deep Learning in Quantitative Finance: Transformer Networks for Time Series Prediction

An SDK for Transformers + YOLO and other SSD family models

Implementation of PyTorch: "GAMBA: MARRY GAUSSIAN SPLATTING WITH MAMBA FOR SINGLE-VIEW 3D RECONSTRUCTION"

Sparse and discrete interpretability tool for neural networks

FoodBERT: Food Extraction with DistilBERT

Official Implementation of MobileUNETR: A Lightweight End-To-End Hybrid Vision Transformer For Efficient Medical Image Segmentation (ECCV2024) (Oral)

Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.

Transformer based Bangla Speech Recognition | Encoder Decoder Architecture

A native macOS lab for teaching tiny language models to think — build the architecture, train the weights, and watch a small LLM emerge from scratch, locally on Apple Silicon with custom data, tokenizers, checkpoints, and MLX acceleration.

Implementation of the transformer from the paper: "Real-World Humanoid Locomotion with Reinforcement Learning"

The purpose of this repository is to introduce new dialogue-level commonsense inference datasets and tasks. We chose dialogues as the data source because dialogues are known to be complex and rich in commonsense.

Run transformers (incl. LLMs) on the Apple Neural Engine.

Implementing RASP transformer programming language https://arxiv.org/pdf/2106.06981.pdf.

ComfyUI nodes for Step Audio EditX - State-of-the-art zero-shot voice cloning and audio editing with emotion, style, speed control, and more.

Platonic Transformers: A Solid Choice For Equivariance (ICML 2026)

[ECCV 2022] "PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation"

Implementation of the world model architecture for self driving out of Wayve