Elgato_dark/Self-Hosting-Guide
1
0
Fork 0
mirror of https://github.com/mikeroyal/Self-Hosting-Guide synced 2026-05-24 09:48:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Updated ChatGPT Chatbots.

Browse source
This commit is contained in:
Michael Royal 2023-04-20 01:01:32 -07:00 committed by GitHub
parent e610d501b1
commit fb6c710c0f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 16 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
README.md
View file

@ -408,7 +408,6 @@ Most self-hosted software can be installed using [Docker](https://en.wikipedia.o
[Varnish](https://www.varnish-cache.org/) - HTTP based web application accelerator focusing on optimizing caching and compression.
### ChatGPT Chatbots
[Back to the Top](#table-of-contents)
@ -466,6 +465,22 @@ npm run dev
Chatbot UI
</p>
[MiniGPT-4](https://minigpt-4.github.io/) is an enhancing Vision-language Understanding with Advanced Large Language Models
**Launching Demo Locally**
Try out the demo [demo.py](https://github.com/Vision-CAIR/MiniGPT-4/blob/main/demo.py) on your local machine by running
```python demo.py --cfg-path eval_configs/minigpt4_eval.yaml --gpu-id 0```
Here, the demo loads Vicuna as 8 bit by default to save some GPU memory usage. Besides, the default beam search width is 1. Under this setting, the **demo cost about 23G GPU memory**. If you have a more powerful GPU with larger GPU memory, you can run the model in 16 bit by setting low_resource to False in the config file [minigpt4_eval.yaml](https://github.com/Vision-CAIR/MiniGPT-4/blob/main/eval_configs/minigpt4_eval.yaml) and use a larger beam search width.
<p align="center">
<img src="https://user-images.githubusercontent.com/45159366/233298431-db46ccd6-c0c8-48db-9d9f-c142776de51f.png">
<br />
MiniGPT-4 Demo
</p>
[GPT4All](https://github.com/nomic-ai/gpt4all) is an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue based on [LLaMa](https://github.com/facebookresearch/llama).
<p align="center">