Luodian

Otter

🦦 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.

RelateAnything

Relate Anything Model is capable of taking an image as input and utilizing SAM to identify the corresponding mask within the image.

Generalizable-Mixture-of-Experts

GMoE could be the next backbone model for many kinds of generalization task.

GenBench

Benchmarking and Analyzing Generative Data for Visual Recognition

IIB

mmc4

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

Awesome-Anything

General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX

langchain_semantic_search

open_flamingo

An open-source framework for training large multimodal models.

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (LLaMA, LLaMa2, ChatGLM2, ChatGPT, Claude, etc) over 50+ datasets.

sglang

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

uncertainty-baselines

High-quality implementations of standard and SOTA methods on a variety of tasks.

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

zsh_codex

This is a ZSH plugin that enables you to use OpenAI's Codex AI in the command line.

3detr

Code & Models for 3DETR - an End-to-end transformer model for 3D object detection

awesome-mixture-of-experts

A collection of AWESOME things about mixture-of-experts

blog

CLIP

Contrastive Language-Image Pretraining

codespace

commands_history

CVinW_Readings

A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''

detectron2

Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.

GPT-4-LLM

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

llama_index

LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data.

luodian.github.io

miro

Official PyTorch implementation of MIRO

openclip

An open source implementation of CLIP with DeepSpeed

OpenPSG

Benchmarking Panoptic Scene Graph Generation (PSG), ECCV'22

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models