github
/
minimind-v
mirror of https://github.com/jingyaogong/minimind-v.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update readme

pull/45/head
gongjy 2025-02-20 23:47:34 +08:00
parent 38a84c2dd2
commit 694ce87e39
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -26,14 +26,14 @@
</div>
* 此项目旨在从0开始，仅用3块钱成本 + 2小时！即可训练出26M参数的超小多模态视觉语言模型**MiniMind-V**。
* 此项目旨在从0开始，仅用1.3块钱成本 + 1小时！即可训练出26M参数的超小多模态视觉语言模型**MiniMind-V**。
* **MiniMind-V**最小版本体积仅为 GPT3 的约 $\frac{1}{7000}$，力求做到个人GPU也可快速推理甚至训练。
* **MiniMind-V**是[MiniMind](https://github.com/jingyaogong/minimind)纯语言模型的视觉能力额外拓展。
* 项目同时包含了VLM大模型的极简结构、数据集清洗、预训练(Pretrain)、监督微调(SFT)等全过程代码。
* 这不仅是一个开源VLM模型的最小实现，也是入门视觉语言模型的简明教程。
* 希望此项目能为所有人提供一个抛砖引玉的示例，一起感受创造的乐趣！推动更广泛AI社区的进步！
> 为防止误解，“2小时” 基于NVIDIA 3090硬件设备（单卡）测试`1 epoch`，“3块钱” 指GPU服务器租用成本。
> 为防止误解，“1小时” 基于NVIDIA 3090硬件设备（单卡）测试`1 epoch`，“1.3块钱” 指GPU服务器租用成本。

8
README_en.md
View File

@ -27,8 +27,8 @@
</div>
* This project aims to train a super-small multimodal vision-language model, **MiniMind-V**, with just a cost of 3 RMB
and 2 hours of work, starting from scratch!
* This project aims to train a super-small multimodal vision-language model, **MiniMind-V**, with just a cost of 1.3 RMB
and 1 hours of work, starting from scratch!
* The smallest version of **MiniMind-V** is only about $\frac{1}{7000}$ the size of GPT-3, designed to enable fast
inference and even training on personal GPUs.
* **MiniMind-V** is an extension of the visual capabilities of the [MiniMind](https://github.com/jingyaogong/minimind)
@ -40,8 +40,8 @@
* The hope is that this project can provide a useful example to inspire others and share the joy of creation, helping to
drive progress in the wider AI community!
> To avoid misunderstandings, the "2 hours" is based on testing (`1 epoch`) with an NVIDIA 3090 hardware device (single GPU), and
> the "3 RMB" refers to GPU server rental costs.
> To avoid misunderstandings, the "1 hours" is based on testing (`1 epoch`) with an NVIDIA 3090 hardware device (single GPU), and
> the "1.3 RMB" refers to GPU server rental costs.
<div align="center">