🩹Editing large language models within 10 seconds⚡

🌐 The Internet OS! Free, Open-Source, and Self-Hostable.

Universal and Transferable Attacks on Aligned Language Models

Enabling PyTorch on XLA Devices (e.g. Google TPU)

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Low-bit optimizers for PyTorch

Implementation of Flash Attention in Jax

The official gpt4free repository | various collection of powerful language models

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

A Unity plugin for using Transformers models in Unity.

[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

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

Implements the SM3-II adaptive optimization algorithm for PyTorch.

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Comprehensive Open-Source Collection of Hindu Sacred Texts including Ramcharitmanas, Bhagavad Gita, Mahabharata, Valmiki Ramayana, Rigveda, Yajurveda, Atharvaveda for Educational and Research Purpo…

maximal update parametrization (µP)

LOMO: LOw-Memory Optimization

This repository contains the code for dataset curation and finetuning of instruct variant of the Bilingual OpenHathi model. The resulting model is meant to follow instructions and chat in Hindi and…

LLM Workshop by Sourab Mangrulkar

Pytorch/XLA SPMD Test code in Google TPU

JAX implementation of the Llama 2 model

A self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".

Pretraining and finetuning for visual instruction following with Mixture of Experts

Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free

Some simple scripts that I use day-to-day when working with LLMs and Huggingface Hub

Tools for merging pretrained large language models.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads