Flexible Python library providing building blocks (layers) for reproducible Transformers research (Tensorflow ✅, Pytorch 🔜, and Jax 🔜)

a lightweight no-dependency fork from transformers.js (only tokenizers)

Julia implementation of the Flash Attention algorithm

Implementation of "With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition, BMVC, 2021" in PyTorch

Manual Fine Tune Sentence Transformer Embeddings

Graph Neural Networks for Expertise Classification on Stack Overflow

WordPiece Tokenizer for BERT models.

Implement common deep networks for computer vision with pytorch from scratch.

🙂🙃 Being happy :) being sad :( with this tool, you become sentiment GIGA chad!

Control LLM token generation by directly manipulating logits to enforce structured outputs. Built with Hugging Face Transformers and demonstrated using Qwen2.5-0.5B.

Needle components for Haystack projects.

ASP.NET Core Web API data pipeline using C# and SQL Server that can extract, transform, and load (ETL) data. The goal is a work with data from multiple sources, process it and store it in a structured format.

This project demonstrates how to fine-tune a pretrained LLaMA 2 model using Hugging Face Transformers and PEFT (LoRA) techniques in Google Colab. The base model, aboonaji/llama2finetune-v2, was loaded from Hugging Face Hub and fine-tuned on a medical text dataset (wiki_medical_terms_llam2_format).

(paused) dna protein prediction using transformer. second version of engima

community response crawler for MapleStort, Nexon

Emotion Sentiment Analysis

Framework for offensive-Language-Detection using Transformer and BiLSTM using two bench mark dataset - OLID and HateXplain.

Sample GPT Transformer Model from Scratch.

Multi-label text classification of movie genres based on their synopsis

GPT implementation following karpathy's lecture.