OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Llava Pp

Llava Pp is a Python research repository extending LLaVA 1.5 with Phi-3 Mini Instruct and LLaMA 3 Instruct for visual-language interaction. It includes model variants, training scripts and links to hosted demos.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Llava Pp — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it to explore LLaVA-based visual-language models built with Phi-3 or LLaMA 3, or to inspect the project’s model variants and training workflow.

Who it is for

  • Researchers comparing or adapting visual-language model variants.
  • Developers exploring image-and-text conversation prototypes.
  • People who want to try the linked Phi-3-V or LLaMA-3-V demos.

Documented uses

  • Ask questions about images through a linked model demo.
  • Explore multimodal conversation using images and text.
  • Compare pretrained, LoRA, merged and fully fine-tuned model variants.
  • Follow documented scripts for pretraining or LoRA fine-tuning.
Before you choose

Requirements & limits

  • The repository links to distinct Phi-3-V and LLaMA-3-V demos, as well as a Colab notebook for Phi-3-V.
  • The model zoo lists pretrained, LoRA, merged and fully fine-tuned variants.
  • Local setup requires initializing Git submodules and installing a specifically pinned Transformers revision.
  • The README does not state hardware requirements.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare the LLaVA++ codebase

Clone the repository, initialize its submodules and install the documented Transformers revision.

Before you start

  • Python project environment
  • Git and pip

Steps

  1. Clone https://github.com/mbzuai-oryx/LLaVA-pp.git.

  2. Change into the LLaVA-pp directory.

  3. Run git submodule update --init --recursive.

  4. Install the specified Transformers revision with the README's pip command.

Expected outcome

The repository and its submodules are checked out, and the documented Transformers revision is installed.

Guide limitations

  • These steps cover setup only; they do not establish that a model has been run.
  • Hardware requirements and further environment details are not specified here.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
6 November 2026
Original website title
mbzuai-oryx/LLaVA-pp · Official homepage title · retained in its source language
How we review sourcesSuggest a correction