LLAVA数据集下载

LLAVA数据集下载

1. Data

Data file name Size
llava_instruct_150k.json 229 MB
llava_instruct_80k.json 229 MB
conversation_58k.json 126 MB
detail_23k.json 20.5 MB
complex_reasoning_77k.json 79.6 MB

1.1 Pretraining Dataset

The pretraining dataset used in this release is a subset of CC-3M dataset, filtered with a more balanced concept coverage distribution. Please see here for a detailed description of the dataset structure and how to download the images.

If you already have CC-3M dataset on your disk, the image names follow this format: GCC_train_000000000.jpg. You may edit the image field correspondingly if necessary.

Data Chat File Meta Data Size
CC-3M Concept-balanced 595K chat.json metadata.json 211 MB
LAION/CC/SBU BLIP-Caption Concept-balanced 558K blip_laion_cc_sbu_558k.json [metadata.json](#Data Chat File Meta Data Size CC-3M Concept-balanced 595K chat.json metadata.json 211 MB LAION/CC/SBU BLIP-Caption Concept-balanced 558K blip_laion_cc_sbu_558k.json metadata.json 181 MB) 181 MB

Important notice : Upon the request from the community, as ~15% images of the original CC-3M dataset are no longer accessible, we upload images.zip for better reproducing our work in research community. It must not be used for any other purposes. The use of these images must comply with the CC-3M license. This may be taken down at any time when requested by the original CC-3M dataset owner or owners of the referenced images.

1.2 GPT-4 Prompts

We provide our prompts and few-shot samples for GPT-4 queries, to better facilitate research in this domain. Please check out the prompts folder for three kinds of questions: conversation, detail description, and complex reasoning.

They are organized in a format of system_message.txt for system message, pairs of abc_caps.txt for few-shot sample user input, and abc_conv.txt for few-shot sample reference output.

Note that you may find them in different format. For example, conversation is in jsonl, and detail description is answer-only. The selected format in our preliminary experiments works slightly better than a limited set of alternatives that we tried: jsonl, more natural format, answer-only. If interested, you may try other variants or conduct more careful study in this. Contributions are welcomed!

2. Visual Instruction Tuning

---------2.1 指令调整数据(instruction tuning data)---------:

LLaVA-Instruct-150K

官方llava_v1_5_mix665k.json

---------2.2 图像(images)---------

COCO

官方train2017

GQA

官方images

OCR-VAQ

官方download script
多线程下载(速度更快)Github解决方案 以及 CSDN解决方案
处理好的数据集下载(方便快捷)Huggingface

TextVQA

官方train_val_images

VisualGenome

官方part1, part2

复制代码
playground
	├──data
	│	├── coco
	│	│   └── train2017
	│	├── gqa
	│	│   └── images
	│	├── ocr_vqa
	│	│   └── images
	│	├── textvqa
	│	│   └── train_images
	│	└── vg
	│	    ├── VG_100K
	│	    └── VG_100K_2
	└── ...   

3. Pretrained Model

---------3.1 语言大模型---------
vicuna-13b-v1.5
vicuna-7b-v1.5
---------3.2 视觉大模型---------
clip-vit-large-patch14-336
---------3.3 LLAVA-1.5预训练模型---------
LLAVA-1.5-13b
LLAVA-1.5-7b
---------3.4 LLAVA-lora微调训练的模型---------
LLAVA-1.5--13b-lora
LLAVA-1.5--7b-lora

相关推荐
Victory_orsh44 分钟前
“自然搞懂”深度学习系列(基于Pytorch架构)——02小试牛刀
人工智能·python·深度学习·神经网络·机器学习
tzc_fly1 小时前
DeepSeek-OCR:上下文光学压缩
人工智能·计算机视觉·ocr
Bruce-li__1 小时前
CI/CD流水线全解析:从概念到实践,结合Python项目实战
开发语言·python·ci/cd
37手游后端团队1 小时前
构建AI会话质检平台:技术架构与实践分享
人工智能·后端
哔哩哔哩技术1 小时前
B站游戏大模型翻译实践 —— 我们如何用LLM撑起全年百万字本地化翻译任务
人工智能
longgyy1 小时前
AI 开发告别 “孤岛”:MCP + 火山引擎
人工智能·火山引擎
珊瑚礁的猪猪侠1 小时前
正则表达式入门到精通教程(Linux实操版)
linux·人工智能·正则表达式
星空的资源小屋1 小时前
MkFont,一款开源免费的字体设计工具
网络·人工智能·pdf·电脑
mir frog1 小时前
DAY44 PYTHON 预训练模型
人工智能·深度学习·机器学习
yuzhuanhei1 小时前
机器学习算法常用算法
人工智能·算法·机器学习