Isaak Carter Augustus
commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,13 @@ datasets:
|
|
| 4 |
- HuggingFaceFW/fineweb
|
| 5 |
- PleIAs/YouTube-Commons
|
| 6 |
- allenai/WildChat-1M
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
language:
|
| 8 |
- de
|
| 9 |
- en
|
|
@@ -13,6 +20,9 @@ library_name: mlx
|
|
| 13 |
tags:
|
| 14 |
- moe
|
| 15 |
- multimodal
|
|
|
|
|
|
|
|
|
|
| 16 |
- j.o.s.i.e.
|
| 17 |
---
|
| 18 |
|
|
@@ -26,12 +36,5 @@ Further more, I will probably make a **UI application** with that model too.
|
|
| 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 and output projections 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>
|
|
|
|
| 4 |
- HuggingFaceFW/fineweb
|
| 5 |
- PleIAs/YouTube-Commons
|
| 6 |
- allenai/WildChat-1M
|
| 7 |
+
- Salesforce/xlam-function-calling-60k
|
| 8 |
+
- ShareGPT4Video/ShareGPT4Video
|
| 9 |
+
- OpenGVLab/ShareGPT-4o
|
| 10 |
+
- TempoFunk/webvid-10M
|
| 11 |
+
- MBZUAI/VideoInstruct-100K
|
| 12 |
+
- MaziyarPanahi/WizardLM_evol_instruct_V2_196k
|
| 13 |
+
- Isaak-Carter/J.O.S.I.E.v3.5
|
| 14 |
language:
|
| 15 |
- de
|
| 16 |
- en
|
|
|
|
| 20 |
tags:
|
| 21 |
- moe
|
| 22 |
- multimodal
|
| 23 |
+
- vision
|
| 24 |
+
- audio
|
| 25 |
+
- endtoend
|
| 26 |
- j.o.s.i.e.
|
| 27 |
---
|
| 28 |
|
|
|
|
| 36 |
Further updates comming soon!!!
|
| 37 |
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
|
| 40 |
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>
|