Commit
•
402ed7d
1
Parent(s):
c192f0b
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,9 +21,17 @@ tags:
|
|
| 21 |
Like **OpenAIs GPT-4o**, it's natively Multimodal, based on the **NExT-GPT** combined with **ROPE**, **RMS Normalisation**, and **MoE**, parred with the **GPT-4o Tokenizer** from OpenAI.
|
| 22 |
This is a *future project* and will take it's time.
|
| 23 |
|
| 24 |
-
|
| 25 |
|
| 26 |
Further updates comming soon!!!
|
| 27 |
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
Source code and more info will be available on my <a href="https://github.com/Goekdeniz-Guelmez/J.O.S.I.E.v4-o.git">GitHub Repo</a>
|
|
|
|
| 21 |
Like **OpenAIs GPT-4o**, it's natively Multimodal, based on the **NExT-GPT** combined with **ROPE**, **RMS Normalisation**, and **MoE**, parred with the **GPT-4o Tokenizer** from OpenAI.
|
| 22 |
This is a *future project* and will take it's time.
|
| 23 |
|
| 24 |
+
Further more, I will probably make a **UI application** with that model too.
|
| 25 |
|
| 26 |
Further updates comming soon!!!
|
| 27 |
|
| 28 |
|
| 29 |
+
First architecture Overview:
|
| 30 |
+
|
| 31 |
+
First Beta will utilize the already pretrained ImageBind Model. The linear input Projection is because the outputs of the ImageBind model are not in the correct dimensions.
|
| 32 |
+
Later on the input projection will be removed.
|
| 33 |
+
|
| 34 |
+
<img src="Architecture_overview_beta3.png" width="100%" height="auto"/>
|
| 35 |
+
|
| 36 |
+
|
| 37 |
Source code and more info will be available on my <a href="https://github.com/Goekdeniz-Guelmez/J.O.S.I.E.v4-o.git">GitHub Repo</a>
|