Nagase-Kotono
commited on
Commit
•
48c6b54
1
Parent(s):
7c81040
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,24 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- tabtoyou/KoLLaVA-CC3M-Pretrain-595K
|
5 |
+
language:
|
6 |
+
- ko
|
7 |
+
tags:
|
8 |
+
- llava
|
9 |
---
|
10 |
+
|
11 |
+
# EEVE-LLaVA-Pretrain-2.8B
|
12 |
+
![이미지](https://cdn.donmai.us/sample/d8/91/__nagase_kotono_idoly_pride_drawn_by_sakuranoron__sample-d8915e20211fe88aba61f1c215cc32d1.jpg)
|
13 |
+
**EEVE-LLaVA-Pretrain-2.8B**
|
14 |
+
|
15 |
+
***This model is a pretrained version of the llava multimodal projector.***
|
16 |
+
|
17 |
+
**You can use this model to finetune** ***[EEVE-Korean-Instruct-2.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-Instruct-2.8B-v1.0)*** **model.**
|
18 |
+
|
19 |
+
|
20 |
+
### Hardware
|
21 |
+
**Using 12x RTX 4090**
|
22 |
+
|
23 |
+
### Software
|
24 |
+
**[MoE-LLaVA](https://github.com/PKU-YuanGroup/MoE-LLaVA)**
|