transformers

AthenaOS is a next generation AI-native operating system managed by Swarms of AI Agents

An open source community implementation of the model from "DIFFERENTIAL TRANSFORMER" paper by Microsoft.

Implementation of a modular, high-performance, and simplistic mamba for high-speed applications

Implementation dino v2 for remote sensing with huggingface transformers

Transformers Pipeline with KoELECTRA

Experiment on NER task using Huggingface state-of-the-art Transformers Natural Language Models library

A simple, consistent and extendable toolkit for IndicTrans2. (Pypi: https://pypi.org/project/indictranstoolkit)

Official resource of the paper "Knowledge Enhanced Masked Language Model for Stance Detection", NAACL 2021

ReAct AI Agent from Scratch using DeepSeek: Handling Memory & Tools without Frameworks

Machine learning robotics engineer preparation material.

A clean, single-file PyTorch implementation of Attention Residuals (Kimi Team, MoonshotAI, 2026), integrated with Grouped Query Attention (GQA), SwiGLU feed-forward networks, and Rotary Position Embeddings (RoPE).

Modular Rust transformer/LLM library using Candle

A extension of Transformers library to include T5ForSequenceClassification class.

Language Model that makes you Laugh .

AI writing assistant with voiced narrator and characters and an illustrator

The first large-scale summarization corpus for the Indonesian language. AACL 2020.

Custom model training using modern architectures. 4-bit QLoRA fine-tuning pipeline for LLaMA 3 8B with production-grade optimization. Memory-efficient training on consumer GPUs. Published adapter on HuggingFace. From training pipeline to deployed model.

Abstractive text summarization by fine-tuning seq2seq models.

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embeddings, RAG and vector search. No Python, no HTTP microservices, no Docker sidecars.

4th Place solution for the Kaggle CommonLit Readability Prize