A comprehensive mathematical tutorial on Transformer models, starting from tokenization and embeddings and progressing through positional encodings, self-attention, and full architecture derivations used in modern NLP models like GPT and BERT.
☆19Jan 8, 2026Updated 7 months ago
Alternatives and similar repositories for transformers-math
Users that are interested in transformers-math are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆18Updated this week
- Implementation of Transformer-based Text-to-Speech models from scratch to enhance speech synthesis, focusing on delivering more natural …☆11Feb 17, 2025Updated last year
- ☆12Jan 11, 2025Updated last year
- Pythoness: use natural language to define Python functions.☆21Apr 22, 2025Updated last year
- Speech to text models; Bidirectional RNN, Attention Model and WaveNet models☆11Nov 6, 2018Updated 7 years ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- End to End Speech to Speech with Emotion System☆15Feb 6, 2025Updated last year
- ☆24Apr 22, 2025Updated last year
- A comprehensive catalog of 34 Retrieval-Augmented Generation (RAG) techniques. Features Python pseudocode, pros/cons, and architecture co…☆70Feb 14, 2026Updated 5 months ago
- A Python implementation of COMO-CMA-ES, a non-elitist multiobjective Evolution Strategy☆17Jan 24, 2026Updated 6 months ago
- Solutions of the CSES Problem Set☆10Nov 24, 2025Updated 8 months ago
- ☆15Mar 19, 2020Updated 6 years ago
- ☆17Dec 12, 2020Updated 5 years ago
- ☆24Jun 9, 2024Updated 2 years ago
- ☆27Jan 22, 2026Updated 6 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Official implementation of "Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning"☆22Oct 3, 2022Updated 3 years ago
- ☆23Feb 21, 2025Updated last year
- ☆11Jan 1, 2024Updated 2 years ago
- A curated list of resources on Document Layout Analysis☆12Aug 7, 2025Updated last year
- Greedy optimizations for Coursera MLOps course☆15Apr 9, 2023Updated 3 years ago
- ☆20Nov 7, 2024Updated last year
- The Chat Application Project is a real-time messaging platform built using Spring Boot, SockJS, and React. It provides a seamless chat ex…☆27Jun 21, 2023Updated 3 years ago
- [ICLR 2025] 🚀 CodeMMLU Evaluator: A framework for evaluating LM models on CodeMMLU MCQs benchmark.☆29Apr 21, 2025Updated last year
- ☆13Apr 25, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- This repo gives a start for the docker.☆38Jan 17, 2024Updated 2 years ago
- A multi-agent system trained with GRPO for reliable long-horizon task planning and execution.☆54Feb 9, 2026Updated 6 months ago
- Create a State of the art excel around any topic, assisted by an LLM!☆18May 25, 2026Updated 2 months ago
- LitServe Examples ⚡ | This repository contains a collection of example applications built using LitServe, a high-performance AI model ser…☆16Aug 3, 2026Updated last week
- A demo example of how to integrate a Spring Boot application with KeyCloak☆21Jul 24, 2025Updated last year
- Code for CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment, Interspeech 2026.☆20Jun 9, 2026Updated 2 months ago
- Graph-based Document Structure Analysis☆18Aug 1, 2026Updated last week
- ☆33Nov 28, 2024Updated last year
- ☆16Oct 17, 2024Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Agent orchestration framework - delegate to Cursor/Codex/Kimi/OpenCode without burning Claude quota☆19Feb 22, 2026Updated 5 months ago
- CORE-ReID: Comprehensive Optimization and Refinement through Ensemble fusion in Domain Adaptation for person re-identification☆16May 7, 2025Updated last year
- A serverless blog platform built with AWS Lambda, DynamoDB, SNS, Cognito, and API Gateway. Backend uses Java 21 + Spring Boot microservic…☆31Jan 13, 2026Updated 6 months ago
- ☆16Apr 12, 2026Updated 3 months ago
- DynamicLink is a lightweight, Firebase-free alternative for handling dynamic links and deep links in web and mobile hybrid environments☆37Feb 5, 2026Updated 6 months ago
- Simple MVC structure for java Servlet and JSP☆13Feb 20, 2025Updated last year
- MCP server connecting AI assistants with Jira & Confluence for smart project management.☆53Aug 10, 2025Updated last year