Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint

Train Models Contrastively in Pytorch

An open source implementation of CLIP.

RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness

[ACL 2024 Demo] SeaLLMs - Large Language Models for Southeast Asia

Multi-Task instruction-tuned LLaMA

code for "Exploiting Reasoning Chains for Multi-hop Science Question Answering"

Source code of "Reasons to Reject? Aligning Language Models with Judgments"

Bring portraits to life!

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

[ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting."

DataComp: In search of the next generation of multimodal datasets

Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities (NeurIPS 2023)

You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

Long Context Transfer from Language to Vision

A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.

VideoHallucer, The first comprehensive benchmark for hallucination detection in large video-language models (LVLMs)

Aligning LMMs with Factually Augmented RLHF

VideoLLM-online: Online Video Large Language Model for Streaming Video (CVPR 2024)

Code for Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models

VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".

Official code for Paper "Mantis: Multi-Image Instruction Tuning"

WebDesignAgent : Towards Effortless Website Creation

This is the official repository of our paper "What If We Recaption Billions of Web Images with LLaMA-3 ?"

A large-scale (194k), Multiple-Choice Question Answering (MCQA) dataset designed to address realworld medical entrance exam questions.