SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

An Open Source Toolkit For LLM Distillation

GABInsight: Exploring Gender-Activity Binding Bias in Vision-Language Models

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

A high-throughput and memory-efficient inference and serving engine for LLMs

Finetune Llama 3.2, Mistral, Phi, Qwen & Gemma LLMs 2-5x faster with 80% less memory

The Memory layer for your AI apps

Adding guardrails to large language models.

A Python package to assess and improve fairness of machine learning models.

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

A comprehensive collection of KAN(Kolmogorov-Arnold Network)-related resources, including libraries, projects, tutorials, papers, and more, for researchers and developers in the Kolmogorov-Arnold N…

Frametime capture and analysis tool

1 Line of code data quality profiling & exploratory data analysis for Pandas and Spark DataFrames.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Goldberg Steam Emulator Generator

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Build AI Agents with memory, knowledge, tools and reasoning. Chat with them using a beautiful Agent UI.

A Python package for easy multiprocessing, but faster than multiprocessing

Kolmogorov Arnold Networks

Hydra is a game launcher with its own embedded bittorrent client

Amir: Free Laravel Accounting Software (فارسی)

A hybrid approach for improving the effectiveness of the k-nearest neighbor algorithm

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Persian NLP Toolkit

The all-in-one AI library for Persian, supporting a wide variety of tasks and modalities!

PyTorch code and models for the DINOv2 self-supervised learning method.