Transformer Architecture Education ML Frameworks

Educational repositories focused on implementing transformer models from scratch to understand core components and mechanisms. Includes tutorials, explanations, and hands-on implementations of attention, positional encoding, and encoder-decoder structures. Does NOT include pre-trained model usage, applications (translation, BERT fine-tuning), or production frameworks.

There are 26 transformer architecture education frameworks tracked. 1 score above 50 (established tier). The highest-rated is lvapeab/nmt-keras at 51/100 with 531 stars.

Get all 26 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=transformer-architecture-education&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

# Framework Score Tier
1 lvapeab/nmt-keras

Neural Machine Translation with Keras

51
Established
2 dair-ai/Transformers-Recipe

🧠 A study guide to learn about Transformers

46
Emerging
3 SirawitC/Transformer_from_scratch_pytorch

Build a transformer model from scratch using pytorch to understand its inner...

44
Emerging
4 jaketae/ensemble-transformers

Ensembling Hugging Face transformers made easy

42
Emerging
5 lof310/transformer

PyTorch implementation of the current SOTA Transformer. Configurable,...

39
Emerging
6 jiangtaoxie/SoT

SoT: Delving Deeper into Classification Head for Transformer

29
Experimental
7 L-Zhe/FasySeq

A fast and easy implementation of Transformer with PyTorch.

29
Experimental
8 leeway0507/Transformer_from_scratch

Transformer 구현 및 학습 방법 설명

27
Experimental
9 anmolg1997/SLM-From-Scratch

Build small language models from scratch — BPE tokenizer, composable...

22
Experimental
10 cosimo17/transformer_notebook

Transformer turorial. Transformer教程

22
Experimental
11 dianjiang75/Transformer

A decoder-only Transformer built entirely from scratch in PyTorch. Trained...

21
Experimental
12 mfarisadip/Multi-X-Transformers

A neural network based on the encoder-decoder architecture the modeling...

20
Experimental
13 msi1427/Original-Transformer-for-Bengali-Translation

A neural machine translation project for Bengali Translation where the...

20
Experimental
14 wj-Mcat/transformer-handbook

add transformer related blogs & codes

19
Experimental
15 Ayush-Aditya/decoder-only-seq2seq

Minimal decoder-only seq2seq pipeline with proper causal masking, teacher...

17
Experimental
16 ankushhKapoor/transformer-from-scratch

Transformer from scratch implementation in PyTorch for Neural Machine...

15
Experimental
17 Banniesdread/decoder-only-seq2seq

Implement a decoder-only Transformer in PyTorch to reverse character...

14
Experimental
18 konodiodaaaaa1/PyTorch-Transformer-From-Scratch

A numerical stable implementation of Transformer from scratch using PyTorch....

14
Experimental
19 sosopop/deepcalc

基于Transformer解码器实现的数学表达式计算器,通过思维链生成中间推理步骤提升计算准确率。本项目可作为学习Transformer架构和推理策略的实践案例。

13
Experimental
20 Joe-Naz01/encoder-decoder

This PyTorch notebook implements a complete Transformer architecture from...

13
Experimental
21 dino65-dev/Transformers

Transformers from scratch implemented GQA,RoPE,RMS-Norm and trained on that code

13
Experimental
22 Xachchchch/deberta-fine-tune-comparison

Experimenting with LoRA vs head-only fine-tuning for DeBERTa on sentiment analysis

13
Experimental
23 Ekoda/LanguageModelFromScratch

An autoregressive transformer language model from first principles, built...

11
Experimental
24 DolbyUUU/Learn_Transformer_from_Easy_to_Hard

一个为初学者设计的 Transformer 分阶段学习项目。通过由简到难的四个阶段,从零开始用 PyTorch 构建完整的 Transformer...

11
Experimental
25 calvin-fei/transformers

Rebuild transformer model from scratch.

11
Experimental
26 JihoonChung/CTC-Product-and-Store-Vectorization

This project is a collaboration between the University of Toronto and...

10
Experimental