Build and run MiniGPT-4: Downfall of GPT-4?
Build and run MiniGPT-4. MiniGPT-4 is a remarkable model that understands images and communicate with a human on the topic. In this video you will see how to run this model yourself. You'd need about 16GB RAM and 16GB GPU in order to run the 7B version of this model.
Github (notebook) link: https://github.com/thushv89/tutorials_deeplearninghero/blob/master/llms/minigpt4.ipynb
MiniGPT-4 Paper: https://arxiv.org/pdf/2304.10592.pdf
MiniGPT-4 Repo: https://github.com/Vision-CAIR/MiniGPT-4
BLIP-2 Paper: https://arxiv.org/pdf/2301.12597.pdf
00:00 - Introduction
00:52 - Introducing BLIP-2 (Base of …
Watch on YouTube ↗
(saves to browser)
Chapters (12)
Introduction
0:52
Introducing BLIP-2 (Base of MiniGPT-4)
5:13
Introducing MiniGPT4
6:07
MiniGPT-4 versions and compute resources
7:13
Set up the environment
7:43
Downloading LLMs
8:27
Caveat: Vicuna versions (v0 vs v1.1)
9:00
Apply Vicuna deltas
9:27
Download MiniGPT4 checkpoint
9:46
Creating MiniGPT4 Chat object
10:23
Inference with MiniGPT-4
12:01
Conclusion
DeepCamp AI