Build software better, together

sharadshukla / imdb-sentiment-classification

Modular IMDb sentiment classification comparing classical ML and PyTorch neural models, with reproducible experiments, smoke-test validation, evaluation, and structured reporting.

python nlp machine-learning deep-neural-networks deep-learning sentiment-analysis scikit-learn imdb pytorch classification portfolio-project self-attention ml-engineering

Updated Aug 25, 2026
Python

endometrial-cashcrop14 / freeciv.andrewmcgrath.info

Star

Host a Freeciv longturn multiplayer server with live status, email alerts, and AI-generated newspaper updates

webgl tutorial canvas multiplayer reverse-engineering bot-api pytorch transformer crawl forecasting outlook pentesting civilization wxpython csdn infosec-reference 4x self-attention

Updated Aug 25, 2026
Shell

Diatomic-assay511 / pytorch-gpt2-persian-sentiment-generation

Star

deep-learning university-project text-generation transformer course-project self-attention review-generation gpt2 positional-embedding decoder-only persian-text-generation causal-attention

Updated Aug 25, 2026
Python

WenjieDu / SAITS

Sponsor

Star

The official PyTorch implementation of the paper "SAITS: Self-Attention-based Imputation for Time Series". A fast and state-of-the-art (SOTA) deep-learning neural network model for efficient time-series imputation (impute multivariate incomplete time series containing NaN missing data/values with machine learning). https://arxiv.org/abs/2202.08516

Updated Aug 25, 2026
Python

omerf-git / Multimodal-ODE-Transfomer-for-ISLR

Star

In this work, we shared the source code which are utilized in the study named ODE Transformers for Isolated Sign Language Recognition: A Study on Robustness and Scalability. This code implements the multimodal experiments which reported in the article.

computer-vision deep-learning pytorch self-attention sign-language-recognition turkish-sign-language isolated-sign-language-recognition ode-transformer autsl-dataset video-transformer-network

Updated Aug 24, 2026
Python

itssouray / self-attention

Star

A from-scratch PyTorch implementation of trainable self-attention, including Q/K/V projections, scaled dot-product attention, backpropagation, and contextual embeddings.

query deep-learning transformers value pytorch embeddings key self-attention contextual-embeddings

Updated Aug 19, 2026
Python

Ad1-stdio / speculative-decoding-engine

Star

machine-learning transformers neural-networks cuda-toolkit self-attention kv-cache llm-inference speculative-decoding

Updated Aug 19, 2026
Python

mmmaximov / sasrec-yambda

Star

SASRec с нуля на PyTorch (causal self-attention вручную) на Yandex Yambda. Аудио-эмбеддинги квантованы в semantic IDs через RQ-VAE: как замена item-эмбеддингов проигрывают, как дополнение дают +39% к NDCG@10 (0.575 vs 0.413). Ablation из шести моделей

pytorch transformer recommender-system yandex-music self-attention sequential-recommendation sasrec rq-vae generative-retrieval semantic-ids yandex-yambda

Updated Aug 17, 2026
Jupyter Notebook

Hamidreza-Talei / decoder-only-transformer-from-scratch

Star

A decoder-only Transformer implemented from scratch in PyTorch for character-level name generation.

natural-language-processing deep-learning transformers text-generation language-modeling pytorch transformer autoregressive character-level self-attention multi-head-attention positional-encoding transformer-from-scratch scaled-dot-product-attention temperature-sampling causal-attention decoder-only-transformer

Updated Aug 17, 2026
Jupyter Notebook

chsiang426 / ML-2021-notes

Star

臺灣大學 (NTU) 李宏毅教授「機器學習 (Machine Learning) 2021 Spring 」課程筆記

machine-learning reinforcement-learning deep-learning cnn transformer gan self-attention self-supervised-learning

Updated Aug 16, 2026

MrEon50 / Global-Context-Layer-GCL-

Star

Lekka warstwa PyTorch dodająca globalny schemat i adaptacyjną kontrolę do Transformerów (O(n) zamiast O(n²)). Pozwala modelowi zobaczyć ogólny obraz sekwencji przed analizą szczegółów.

nlp machine-learning deep-learning pytorch transformer neural-networks attention-mechanism self-attention huggingface global-context llm-architecture

Updated Aug 16, 2026
Python

weihuaguo270-ops / llm-inference-pipeline

Star

LLM 推理性能决策基线：TTFT/TPOT、KV Cache、吞吐与解码策略对照

Updated Aug 20, 2026
Python

pashtari / deconver

Star

Official PyTorch Implementation of "Deconver: A Deconvolutional Network for Medical Image Segmentation"

deep-learning transformer segmentation deconvolution self-attention medical-image-segmentation

Updated Aug 14, 2026
Python

iblameandrew / qualitative-self-attention

Star

Watch a transformer block as a living agent society.

game-of-life educational-project conways-game-of-life self-attention simulacra

Updated Aug 14, 2026
Python

mrabeeumar / GPT-from-scratch

Star

GPT-style decoder-only Transformer built from scratch in PyTorch — custom byte-level BPE tokenizer, causal multi-head self-attention, Pre-LN Transformer blocks, and end-to-end training on WikiText-2. 9 experiments reduced test perplexity 120.79 → 73.76, with an 8.6M-parameter model outperforming larger runs.

nlp machine-learning deep-learning pytorch transformer gpt from-scratch tokenization self-attention byte-pair-encoding llm generative-ai

Updated Aug 13, 2026
Jupyter Notebook

Ayush-2703 / FT-Transformer

Star

PyTorch implementation of the FT-Transformer (Gorishniy et al., 2021) for tabular regression — benchmarked against classical baselines on California Housing, with ablation studies, Optuna tuning, 98% test coverage, and CI/CD.

deep-learning tabular-data regression pytorch transformer self-attention pytorch-implementation self-attention-implementation tabular-deep-learning feature-tokenizer