linxid

finetune-fuyu

example showing finetuning of fuyu

llama_index

LlamaIndex is a data framework for your LLM applications

llama-lab

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

SwissArmyTransformer

SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.

Auto-GPT-Plugin-google-scholar

A starting point for developing your own plug-in for Auto-GPT

DataOptim

A collection of visual instruction tuning datasets.

Monkey

【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models

LLaMA-VID

Official Implementation for LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

Efficient-LLMs-Survey

[TMLR 2024] Efficient Large Language Models: A Survey

phd

A list of resources on how/why to do a PhD

Awesome-LLM-Compression

Awesome LLM compression research papers and tools.

BMCook

Model Compression for Big Models

WeChatMsg

提取微信聊天记录，将其导出成HTML、Word、Excel文档永久保存，对聊天记录进行分析生成年度聊天报告，用聊天数据训练专属于个人的AI聊天助手

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

mlx

MLX: An array framework for Apple silicon

Image-Analysis-with-Azure-Computer-Vision-4.0

Image-Analysis-with-Azure-Computer-Vision-4.0

marker

Convert PDF to markdown quickly with high accuracy

CogVLM

a state-of-the-art-level open visual language model | 多模态预训练模型

blog

llm-action

本项目旨在分享大模型相关技术原理以及实战经验。

ColossalAI

Making large AI models cheaper, faster and more accessible

UNITER

Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"

MM-Navigator

sam-hq

Segment Anything in High Quality [NeurIPS 2023]

groundingLMM

[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.

Yi

A series of large language models trained from scratch by developers @01-ai

LingCloud

Attaching human-like eyes to the large language model

PALI3

Implementation of PALI3 from the paper PALI-3 VISION LANGUAGE MODELS: SMALLER, FASTER, STRONGER"

flamingo-pytorch

Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch