StarCycle commited on
Commit
76955fd
1 Parent(s): 31f875a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ llava-siglip-internlm2-1_8b-pretrain-v1 is a LLaVA checkpoint finetuned from [in
13
 
14
  The total size of the model is around 2.2B, which is suitable for embedded applications like robotics. This model performs slightly better than [llava-clip-internlm2-1_8b-v1](https://huggingface.co/StarCycle/llava-clip-internlm2-1_8b-v1).
15
 
16
- #### By the way, it's also stronger than MiniCPM-V in the test split on MMBench.
17
 
18
  I have not carefully tune the hyperparameters during training. If you have any idea to improve it, please open an issue or just send an email to zhuohengli@foxmail.com. You are welcomed!
19
 
 
13
 
14
  The total size of the model is around 2.2B, which is suitable for embedded applications like robotics. This model performs slightly better than [llava-clip-internlm2-1_8b-v1](https://huggingface.co/StarCycle/llava-clip-internlm2-1_8b-v1).
15
 
16
+ #### By the way, it's also stronger than MiniCPM-V in the test split on MMBench, with vert basic datasets and network design. Our model size is also smaller.
17
 
18
  I have not carefully tune the hyperparameters during training. If you have any idea to improve it, please open an issue or just send an email to zhuohengli@foxmail.com. You are welcomed!
19