Nagase-Kotono commited on
Commit
eb4a299
1 Parent(s): bf32684

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -0
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - tabtoyou/KoLLaVA-CC3M-Pretrain-595K
5
+ ---
6
+ # EEVE-LLaVA-2.8B-CLIP_KO-pretrain
7
+
8
+ ![이미지](https://cdn.donmai.us/sample/d8/91/__nagase_kotono_idoly_pride_drawn_by_sakuranoron__sample-d8915e20211fe88aba61f1c215cc32d1.jpg)
9
+
10
+ **This model is a pretrained version of the llava multimodal projector.**
11
+
12
+ **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.**
13
+
14
+ **Use [Bingsu/clip-vit-large-patch14-ko](https://huggingface.co/Bingsu/clip-vit-large-patch14-ko)**
15
+
16
+ ## Hardware
17
+ ***3x NVIDIA A100 40GB***
18
+ ## Software
19
+ ***Using [MoE-LLaVA](https://github.com/PKU-YuanGroup/MoE-LLaVA)***