
CuMo
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
Stars: 94

CuMo is a project focused on scaling multimodal Large Language Models (LLMs) with Co-Upcycled Mixture-of-Experts. It introduces CuMo, which incorporates Co-upcycled Top-K sparsely-gated Mixture-of-experts blocks into the vision encoder and the MLP connector, enhancing the capabilities of multimodal LLMs. The project adopts a three-stage training approach with auxiliary losses to stabilize the training process and maintain a balanced loading of experts. CuMo achieves comparable performance to other state-of-the-art multimodal LLMs on various Visual Question Answering (VQA) and visual-instruction-following benchmarks.
README:
Jiachen Li, Xinyao Wang, Sijie Zhu, Chia-wen Kuo, Lu Xu, Fan Chen, Jitesh Jain, Humphrey Shi, Longyin Wen
- [06/07] We released checkpoints of CuMo after pre-training and pre-finetuning stages at CuMo-misc.
- [05/10] Check out the Demo based on Gradio zero gpu space.
- [05/09] Check out the Arxiv version of the paper!
- [05/08] We released CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts with project page and codes.
- Release
- Contents
- Overview
- Installation
- Model Zoo
- Demo setup
- Getting Started
- Citation
- Acknowledgement
- License
In this project, we delve into the usage and training recipe of leveraging MoE in multimodal LLMs. We propose CuMo, which incorporates Co-upcycled Top-K sparsely-gated Mixture-of-experts blocks into the vision encoder and the MLP connector, thereby enhancing the capabilities of multimodal LLMs. We further adopt a three-stage training approach with auxiliary losses to stabilize the training process and maintain a balanced loading of experts. CuMo is exclusively trained on open-sourced datasets and achieves comparable performance to other state-of-the-art multimodal LLMs on multiple VQA and visual-instruction-following benchmarks.
- Clone this repo.
git clone https://github.com/SHI-Labs/CuMo.git
cd CuMo
- Install dependencies.
We used python 3.9 venv for all experiments and it should be compatible with python 3.9 or 3.10 under anaconda if you prefer to use it.
venv:
python -m venv /path/to/new/virtual/cumo
source /path/to/new/virtual/cumo/bin/activate
anaconda:
conda create -n cumo python=3.9 -y
conda activate cumo
pip install --upgrade pip
pip install -e .
- Install additional packages for training CuMo
pip install -e ".[train]"
pip install flash-attn --no-build-isolation
The CuMo model weights are open-sourced at Huggingface:
Model | Base LLM | Vision Encoder | MLP Connector | Download |
---|---|---|---|---|
CuMo-7B | Mistral-7B-Instruct-v0.2 | CLIP-MoE | MLP-MoE | 🤗 HF ckpt |
CuMo-8x7B | Mixtral-8x7B-Instruct-v0.1 | CLIP-MoE | MLP-MoE | 🤗 HF ckpt |
The intermediate checkpoints after pre-training and pre-finetuning are also released at Huggingface:
Model | Base LLM | Stage | Download |
---|---|---|---|
CuMo-7B | Mistral-7B-Instruct-v0.2 | Pre-Training | 🤗 HF ckpt |
CuMo-8x7B | Mixtral-8x7B-Instruct-v0.1 | Pre-Finetuning | 🤗 HF ckpt |
We provide a Gradio Web UI based demo. You can also setup the demo locally with
CUDA_VISIBLE_DEVICES=0 python -m cumo.serve.app \
--model-path checkpoints/CuMo-mistral-7b
you can add --bits 8
or --bits 4
to save the GPU memory.
If you prefer to star a demo without a web UI, you can use the following commands to run a demo with CuMo-Mistral-7b on your terminal:
CUDA_VISIBLE_DEVICES=0 python -m cumo.serve.cli \
--model-path checkpoints/CuMo-mistral-7b \
--image-file cumo/serve/examples/waterview.jpg
you can add --load-4bit
or --load-8bit
to save the GPU memory.
Please refer to Getting Started for dataset preparation, training, and inference details of CuMo.
@article{li2024cumo,
title={CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts},
author={Li, Jiachen and Wang, Xinyao and Zhu, Sijie and Kuo, Chia-wen and Xu, Lu and Chen, Fan and Jain, Jitesh and Shi, Humphrey and Wen, Longyin},
journal={arXiv:},
year={2024}
}
We thank the authors of LLaVA, MoE-LLaVA, S^2, st-moe-pytorch, mistral-src for releasing the source codes.
The weights of checkpoints are licensed under CC BY-NC 4.0 for non-commercial use. The codebase is licensed under Apache 2.0. This project utilizes certain datasets and checkpoints that are subject to their respective original licenses. Users must comply with all terms and conditions of these original licenses. The content produced by any version of CuMo is influenced by uncontrollable variables such as randomness, and therefore, the accuracy of the output cannot be guaranteed by this project. This project does not accept any legal liability for the content of the model output, nor does it assume responsibility for any losses incurred due to the use of associated resources and output results.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for CuMo
Similar Open Source Tools

CuMo
CuMo is a project focused on scaling multimodal Large Language Models (LLMs) with Co-Upcycled Mixture-of-Experts. It introduces CuMo, which incorporates Co-upcycled Top-K sparsely-gated Mixture-of-experts blocks into the vision encoder and the MLP connector, enhancing the capabilities of multimodal LLMs. The project adopts a three-stage training approach with auxiliary losses to stabilize the training process and maintain a balanced loading of experts. CuMo achieves comparable performance to other state-of-the-art multimodal LLMs on various Visual Question Answering (VQA) and visual-instruction-following benchmarks.

SeerAttention
SeerAttention is a novel trainable sparse attention mechanism that learns intrinsic sparsity patterns directly from LLMs through self-distillation at post-training time. It achieves faster inference while maintaining accuracy for long-context prefilling. The tool offers features such as trainable sparse attention, block-level sparsity, self-distillation, efficient kernel, and easy integration with existing transformer architectures. Users can quickly start using SeerAttention for inference with AttnGate Adapter and training attention gates with self-distillation. The tool provides efficient evaluation methods and encourages contributions from the community.

PowerInfer
PowerInfer is a high-speed Large Language Model (LLM) inference engine designed for local deployment on consumer-grade hardware, leveraging activation locality to optimize efficiency. It features a locality-centric design, hybrid CPU/GPU utilization, easy integration with popular ReLU-sparse models, and support for various platforms. PowerInfer achieves high speed with lower resource demands and is flexible for easy deployment and compatibility with existing models like Falcon-40B, Llama2 family, ProSparse Llama2 family, and Bamboo-7B.

langtest
LangTest is a comprehensive evaluation library for custom LLM and NLP models. It aims to deliver safe and effective language models by providing tools to test model quality, augment training data, and support popular NLP frameworks. LangTest comes with benchmark datasets to challenge and enhance language models, ensuring peak performance in various linguistic tasks. The tool offers more than 60 distinct types of tests with just one line of code, covering aspects like robustness, bias, representation, fairness, and accuracy. It supports testing LLMS for question answering, toxicity, clinical tests, legal support, factuality, sycophancy, and summarization.

VideoTuna
VideoTuna is a codebase for text-to-video applications that integrates multiple AI video generation models for text-to-video, image-to-video, and text-to-image generation. It provides comprehensive pipelines in video generation, including pre-training, continuous training, post-training, and fine-tuning. The models in VideoTuna include U-Net and DiT architectures for visual generation tasks, with upcoming releases of a new 3D video VAE and a controllable facial video generation model.

TxAgent
TxAgent is an AI agent designed for precision therapeutics, leveraging multi-step reasoning and real-time biomedical knowledge retrieval across a toolbox of 211 tools. It evaluates drug interactions, contraindications, and tailors treatment strategies to individual patient characteristics. TxAgent outperforms leading models across various drug reasoning tasks and personalized treatment scenarios, ensuring treatment recommendations align with clinical guidelines and real-world evidence.

NeMo-Curator
NeMo Curator is a GPU-accelerated open-source framework designed for efficient large language model data curation. It provides scalable dataset preparation for tasks like foundation model pretraining, domain-adaptive pretraining, supervised fine-tuning, and parameter-efficient fine-tuning. The library leverages GPUs with Dask and RAPIDS to accelerate data curation, offering customizable and modular interfaces for pipeline expansion and model convergence. Key features include data download, text extraction, quality filtering, deduplication, downstream-task decontamination, distributed data classification, and PII redaction. NeMo Curator is suitable for curating high-quality datasets for large language model training.

rllm
rLLM is an open-source framework for post-training language agents via reinforcement learning. With rLLM, you can easily build your custom agents and environments, train them with reinforcement learning, and deploy them for real-world workloads. The framework provides tools for training coding models, software engineering agents, and language agents using reinforcement learning techniques. It supports various models of different sizes and capabilities, enabling users to achieve state-of-the-art performance in coding and language-related tasks. rLLM is designed to be user-friendly, scalable, and efficient for training and deploying language agents in diverse applications.

crab
CRAB is a framework for building LLM agent benchmark environments in a Python-centric way. It is cross-platform and multi-environment, allowing the creation of agent environments supporting various deployment options. The framework offers easy-to-use configuration with the ability to add new actions and define environments seamlessly. CRAB also provides a novel benchmarking suite with tasks and evaluators defined in Python, along with a unique graph evaluator method for detailed metrics.

LLM-Pruner
LLM-Pruner is a tool for structural pruning of large language models, allowing task-agnostic compression while retaining multi-task solving ability. It supports automatic structural pruning of various LLMs with minimal human effort. The tool is efficient, requiring only 3 minutes for pruning and 3 hours for post-training. Supported LLMs include Llama-3.1, Llama-3, Llama-2, LLaMA, BLOOM, Vicuna, and Baichuan. Updates include support for new LLMs like GQA and BLOOM, as well as fine-tuning results achieving high accuracy. The tool provides step-by-step instructions for pruning, post-training, and evaluation, along with a Gradio interface for text generation. Limitations include issues with generating repetitive or nonsensical tokens in compressed models and manual operations for certain models.

ALMA
ALMA (Advanced Language Model-based Translator) is a many-to-many LLM-based translation model that utilizes a two-step fine-tuning process on monolingual and parallel data to achieve strong translation performance. ALMA-R builds upon ALMA models with LoRA fine-tuning and Contrastive Preference Optimization (CPO) for even better performance, surpassing GPT-4 and WMT winners. The repository provides ALMA and ALMA-R models, datasets, environment setup, evaluation scripts, training guides, and data information for users to leverage these models for translation tasks.

RLAIF-V
RLAIF-V is a novel framework that aligns MLLMs in a fully open-source paradigm for super GPT-4V trustworthiness. It maximally exploits open-source feedback from high-quality feedback data and online feedback learning algorithm. Notable features include achieving super GPT-4V trustworthiness in both generative and discriminative tasks, using high-quality generalizable feedback data to reduce hallucination of different MLLMs, and exhibiting better learning efficiency and higher performance through iterative alignment.

keras-llm-robot
The Keras-llm-robot Web UI project is an open-source tool designed for offline deployment and testing of various open-source models from the Hugging Face website. It allows users to combine multiple models through configuration to achieve functionalities like multimodal, RAG, Agent, and more. The project consists of three main interfaces: chat interface for language models, configuration interface for loading models, and tools & agent interface for auxiliary models. Users can interact with the language model through text, voice, and image inputs, and the tool supports features like model loading, quantization, fine-tuning, role-playing, code interpretation, speech recognition, image recognition, network search engine, and function calling.

vim-airline
Vim-airline is a lean and mean status/tabline plugin for Vim that provides a nice statusline at the bottom of each Vim window. It consists of several sections displaying information such as mode, environment status, filename, filetype, file encoding, and current position in the file. The plugin is highly customizable and integrates with various plugins, providing a tiny core with extensibility in mind. It is optimized for speed, supports multiple themes, and integrates seamlessly with other plugins. Vim-airline is written in 100% Vimscript, eliminating the need for Python. The plugin aims to be stable and includes a unit testing suite for reliability.

chronos-forecasting
Chronos is a family of pretrained time series forecasting models based on language model architectures. A time series is transformed into a sequence of tokens via scaling and quantization, and a language model is trained on these tokens using the cross-entropy loss. Once trained, probabilistic forecasts are obtained by sampling multiple future trajectories given the historical context. Chronos models have been trained on a large corpus of publicly available time series data, as well as synthetic data generated using Gaussian processes.

evalverse
Evalverse is an open-source project designed to support Large Language Model (LLM) evaluation needs. It provides a standardized and user-friendly solution for processing and managing LLM evaluations, catering to AI research engineers and scientists. Evalverse supports various evaluation methods, insightful reports, and no-code evaluation processes. Users can access unified evaluation with submodules, request evaluations without code via Slack bot, and obtain comprehensive reports with scores, rankings, and visuals. The tool allows for easy comparison of scores across different models and swift addition of new evaluation tools.
For similar tasks

CuMo
CuMo is a project focused on scaling multimodal Large Language Models (LLMs) with Co-Upcycled Mixture-of-Experts. It introduces CuMo, which incorporates Co-upcycled Top-K sparsely-gated Mixture-of-experts blocks into the vision encoder and the MLP connector, enhancing the capabilities of multimodal LLMs. The project adopts a three-stage training approach with auxiliary losses to stabilize the training process and maintain a balanced loading of experts. CuMo achieves comparable performance to other state-of-the-art multimodal LLMs on various Visual Question Answering (VQA) and visual-instruction-following benchmarks.

BlueLM
BlueLM is a large-scale pre-trained language model developed by vivo AI Global Research Institute, featuring 7B base and chat models. It includes high-quality training data with a token scale of 26 trillion, supporting both Chinese and English languages. BlueLM-7B-Chat excels in C-Eval and CMMLU evaluations, providing strong competition among open-source models of similar size. The models support 32K long texts for better context understanding while maintaining base capabilities. BlueLM welcomes developers for academic research and commercial applications.

model_server
OpenVINOâ„¢ Model Server (OVMS) is a high-performance system for serving models. Implemented in C++ for scalability and optimized for deployment on Intel architectures, the model server uses the same architecture and API as TensorFlow Serving and KServe while applying OpenVINO for inference execution. Inference service is provided via gRPC or REST API, making deploying new algorithms and AI experiments easy.

TaskingAI
TaskingAI brings Firebase's simplicity to **AI-native app development**. The platform enables the creation of GPTs-like multi-tenant applications using a wide range of LLMs from various providers. It features distinct, modular functions such as Inference, Retrieval, Assistant, and Tool, seamlessly integrated to enhance the development process. TaskingAI’s cohesive design ensures an efficient, intelligent, and user-friendly experience in AI application development.

MathCoder
MathCoder is a repository focused on enhancing mathematical reasoning by fine-tuning open-source language models to use code for modeling and deriving math equations. It introduces MathCodeInstruct dataset with solutions interleaving natural language, code, and execution results. The repository provides MathCoder models capable of generating code-based solutions for challenging math problems, achieving state-of-the-art scores on MATH and GSM8K datasets. It offers tools for model deployment, inference, and evaluation, along with a citation for referencing the work.

llm_qlora
LLM_QLoRA is a repository for fine-tuning Large Language Models (LLMs) using QLoRA methodology. It provides scripts for training LLMs on custom datasets, pushing models to HuggingFace Hub, and performing inference. Additionally, it includes models trained on HuggingFace Hub, a blog post detailing the QLoRA fine-tuning process, and instructions for converting and quantizing models. The repository also addresses troubleshooting issues related to Python versions and dependencies.

instruct-ner
Instruct NER is a solution for complex Named Entity Recognition tasks, including Nested NER, based on modern Large Language Models (LLMs). It provides tools for dataset creation, training, automatic metric calculation, inference, error analysis, and model implementation. Users can create instructions for LLM, build dictionaries with labels, and generate model input templates. The tool supports various entity types and datasets, such as RuDReC, NEREL-BIO, CoNLL-2003, and MultiCoNER II. It offers training scripts for LLMs and metric calculation functions. Instruct NER models like Llama, Mistral, T5, and RWKV are implemented, with HuggingFace models available for adaptation and merging.

rknn-llm
RKLLM software stack is a toolkit designed to help users quickly deploy AI models to Rockchip chips. It consists of RKLLM-Toolkit for model conversion and quantization, RKLLM Runtime for deploying models on Rockchip NPU platform, and RKNPU kernel driver for hardware interaction. The toolkit supports RK3588 and RK3576 series chips and various models like TinyLLAMA, Qwen, Phi, ChatGLM3, Gemma, InternLM2, and MiniCPM. Users can download packages, docker images, examples, and docs from RKLLM_SDK. Additionally, RKNN-Toolkit2 SDK is available for deploying additional AI models.
For similar jobs

sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.