PyPI Stats
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About
Home

Multi Modality Python Packages

Python packages with the GitHub topic multi-modality. Sorted by relevance, with stars and monthly downloads.
hanxiao
bert-serving-client

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

7K 13K 2K
hanxiao
bert-serving-server

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

7K 13K 2K
jina-ai
clip-as-service

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

6K 13K 2K
jina-ai
clip-client

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

6K 13K 2K
jina-ai
clip-server

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

5K 13K 2K
lucidrains
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

3K 4K 310
jina-ai
open-gpt-torch

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

2K 167 22
kyegomez
gemini-torch

Gemini - Pytorch

1K 466 64
haotian-liu
llava-torch

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

858 25K 3K
dvlab-research
visionzip

Official repository for VisionZip (CVPR 2025)

685 427 23
kyegomez
sophia-optimizer

Sophia Optimizer ULTRA FAST

603 382 26
kyegomez
andromeda-llm

andromeda - Pytorch

537 151 22
kyegomez
andromeda-torch

Andromeda - Pytorch

497 151 22
Luodian
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.

368 3K 212
kyegomez
tiny-gptv

Simple Implementation of TinyGPTV in super simple Zeta lego blocks

367 16 0
kyegomez
hsss

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

366 15 2
kyegomez
mm1-torch

MM1 - Pytorch

356 27 1
kyegomez
the-compiler

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

318 145 17
kyegomez
hrtx

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

284 15 3
kyegomez
qformer

Implementation of Qformer from BLIP2 in Zeta Lego blocks.

253 49 2
jina-ai
rungpt

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

250 167 22
kyegomez
thebestllmever

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

242 151 22
kyegomez
andromeda-transformer

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

237 151 22
jina-ai
v-clip-server

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

221 13K 2K
    • Data from PyPI, GitHub, ClickHouse, and BigQuery