Text Generation
Transformers
PyTorch
English
llava_mistral
pharaouk commited on
Commit
a929bf9
·
1 Parent(s): 30993fc

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #BakLLaVA 1
2
+
3
+ BakLLaVA 1 is a Mistral 7B base augmented with the LLaVA 1.5 architecture. In this first version, we showcase that a Mistral 7B base outperforms Llama 2 13B on several benchmarks.
4
+
5
+
6
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b7e345f92b20f7a38bf47a/qdYubrBmF7ztAHgdfkkwG.png)
7
+
8
+
9
+ BakLLaVA 2 is cooking with a significantly larger dataset and a novel architecture that expands beyond the current LLaVA method.
10
+
11
+