Experiments for our CLEAR benchmark of unlearning methods in a multimodal setup

FacTool: Factuality Detection in Generative AI

Installing hardware-accelerated PyTorch with Poetry on different hardware using the same `pyproject.toml`

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

[EMNLP 2024 Industry track] MERLIN : Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline

CUDA Templates for Linear Algebra Subroutines

The related works and background techniques about Openai o1

MuLe: Multi-Grained Graph Learning for Multi-Behavior Recommendation (CIKM 2024)

Improving Text Embedding of Language Models Using Contrastive Fine-tuning

Tools for understanding how transformer predictions are built layer-by-layer

LLM101n: Let's build a Storyteller

Official Pytorch implementation of LinCIR: Language-only Training of Zero-shot Composed Image Retrieval (CVPR 2024)

Code for AAAI'24 paper "Graph Neural Prompting with Large Language Models".

Learning to Tokenize for Generative Retrieval (NeurIPS 2023)

Data and info for the paper "ParaDetox: Text Detoxification with Parallel Data"

The official Meta Llama 3 GitHub site

Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)

Solutions to the problems in the book: Linear Algebra and Learning from Data by Gilbert Strang, MIT

Minimal Implementation of a D3PM in pytorch

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)

LLM training in simple, raw C/CUDA

A framework for few-shot evaluation of language models.

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.