VegB

mmc4

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

texar

Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the CASL project: http://casl-project.ai/

open_flamingo

An open-source framework for training large multimodal models.

Diagnose_VLN

Code for "Diagnosing Vision-and-language Navigation: What Really Matters"

iNLG

Implementation of "Visualize Before You Write: Imagination-Guided Open-Ended Text Generation".

LLaMA-Adapter

Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

MiniGPT-4

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

mPLUG-Owl

mPLUG-Owl🦉: Modularization Empowers Large Language Models with Multimodality

Text_Infilling

Source code for Text Infilling, implemented with Texar.

VLN-Transformer

Implementation of "Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation"

VegB/Text_Infilling

Source code for Text Infilling, implemented with Texar.

VegB/VLN-Transformer

Implementation of "Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation"

VegB/iNLG

Implementation of "Visualize Before You Write: Imagination-Guided Open-Ended Text Generation".

VegB/Diagnose_VLN

Code for "Diagnosing Vision-and-language Navigation: What Really Matters"

VegB/LLaMA-Adapter

Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

VegB/MiniGPT-4

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

VegB/mPLUG-Owl

mPLUG-Owl🦉: Modularization Empowers Large Language Models with Multimodality

VegB/wanrongzhu-website