https://github.com/adithya-s-k/eagle

A framework streamlining Training, Finetuning, Evaluation and Deployment of Multi Modal Language models

https://github.com/adithya-s-k/eagle

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (12.3%) to scientific vocabulary

Keywords

llm multimodal-large-language-models vlm
Last synced: 6 months ago · JSON representation

Repository

A framework streamlining Training, Finetuning, Evaluation and Deployment of Multi Modal Language models

Basic Info
  • Host: GitHub
  • Owner: adithya-s-k
  • License: apache-2.0
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 52.7 KB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
llm multimodal-large-language-models vlm
Created almost 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme License

README.md

Eagle

A framework streamlining Training, Finetuning, Evaluation and Deployment of Multi Modal Language models

Features

  • Diverse Model Support: Llama3, Phi, Mistral, Gemma, and more.
  • Versatile Image Encoding: CLIP, Seglip, RADIO, and others.
  • Customization Made Simple: YAML files and CLI for adaptability.
  • Efficient Resource Utilization: Seamless operation on a single GPU.
  • Seamless Deployment: Docker locally or on cloud with Skypilot.
  • Comprehensive Documentation: Includes datasets for successful implementation.

Table of Content

  1. Introduction
  2. Supported_Models
  3. Changelog
  4. Installation
  5. Pretrain
  6. Finetune
  7. Evaluate
  8. Inference
  9. Features to be Added
  10. Citation

11. Acknowledgement

SUPPORTED MODELS

LLMS

  • Llama3
  • Phi
  • Mistral
  • Gemma

Vision Encoder/Transformer

Audio Encoder/Transformer

Video Encode/Transformer

Multi Model

CHANGLE LOGS (What's New)

  • Version 1.0.1:
    • Added support for distributed training.
    • Included accelerate library.
  • Version 1.0.0:
    • Initial release.

Installation

  1. Clone the repository from GitHub.
  2. Install dependencies using pip: pip install -r requirements.txt.
  3. Run setup.sh to set up the environment.
  4. Start using Eagle!

PRETRAIN

  • Utilize supported models for pretraining multimodal models.

FINETUNE

  • Fine-tune pretrained models with custom datasets or tasks.

EVALUATE

  • Evaluate model performance using specified metrics and datasets.

INFERENCE/DEPLOY

  • Deploy models for inference on new data or integrate them into existing systems.

Features to be Added

  • Add support for accelerate.
  • Add support for additional Huggingface models such as falcon, mpt.

CITATION

@article{AdithyaSKolavi2024, title={Eagle: Unified Platform to train multimodal models}, author={Adithya S Kolavi}, year={2024}, url={https://github.com/adithya-s-k/eagle} }

ACKNOWLEDGEMENT

We would like to express our gratitude to the creators of LLaVA (Large Language and Vision Assistant) for providing the groundwork for our project. Visit their repository here.

Owner

  • Name: Adithya S K
  • Login: adithya-s-k
  • Kind: user
  • Location: Indian
  • Company: Cognitivelab

Exploring Generative AI • Google DSC Lead'23 • Cloud & Full Stack Engineer • Drones & IoT • FOSS Contributor

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Issues and Pull Requests

Last synced: 11 months ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels