Multi Modality Python Packages

bert-serving-client

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

bert-serving-server

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

clip-as-service

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

clip-client

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

clip-server

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

deep-daze

Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun

open-gpt-torch

An open-source cloud-native of large multi-modal models (LMMs) serving framework.

gemini-torch

The open source implementation of Gemini, the model that will "eclipse ChatGPT" by Google

andromeda-llm

An all-new Language Model That Processes Ultra-Long Sequences of 100,000+ Ultra-Fast

sophia-optimizer

Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.

rungpt

An open-source cloud-native of large multi-modal models (LMMs) serving framework.

tiny-gptv

Simple Implementation of TinyGPTV in super simple Zeta lego blocks

geminix

The open source implementation of Gemini, the model that will "eclipse ChatGPT" by Google

thebestllmever

An all-new Language Model That Processes Ultra-Long Sequences of 100,000+ Ultra-Fast

open-gpts

An open-source cloud-native of large multi-modal models (LMMs) serving framework.

hsss

Implementation of a Hierarchical Mamba as described in the paper: "Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling"

andromeda-torch

An all-new Language Model That Processes Ultra-Long Sequences of 100,000+ Ultra-Fast

otter-ai

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

hrtx

Multi-Modal Multi-Embodied Hivemind-like Iteration of RTX-2

the-compiler

Seed, Code, Harvest: Grow Your Own App with Tree of Thoughts!

llava-torch

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

fuyu

Implementation of Adepts Fuyu all-new Multi-Modality model in pytorch

qformer

Implementation of Qformer from BLIP2 in Zeta Lego blocks.

mm1-torch

PyTorch Implementation of the paper "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"