Update README.md

README.md

@@ -1,11 +1,34 @@
-*BakLLaVA 1
+---
+datasets:
+- SkunkworksAI/BakLLaVA-1-FT
+language:
+- en
+library_name: transformers
+license: apache-2.0
+---
+
+<p><h1> BakLLaVA-1 </h1></p>
+
+Thank you to our compute sponsors Together Compute (www.together.ai).
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b7e345f92b20f7a38bf47a/V5lpOHWGGYJ2yPpEo_8i1.png)
 
 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. 
+You can run BakLLaVA-1 on the current LLaVA-1.5 inference code (https://llava-vl.github.io/). We are currently updating our repo to make it easier. (https://github.com/SkunkworksAI/BakLLaVA).
+
+
+Note: BakLLaVA-1 is fully open-source but was trained on certain data that includes LLaVA's corpus which is not commercially permissive. We will fix this in the upcoming release.
+
+
+BakLLaVA 2 is cooking with a significantly larger (commercially viable) dataset and a novel architecture that expands beyond the current LLaVA method. BakLLaVA-2 will do away with the restrictions of BakLLaVA-1.
+
+
+# Evaluations
 
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b7e345f92b20f7a38bf47a/qdYubrBmF7ztAHgdfkkwG.png)
 
 
-BakLLaVA 2 is cooking with a significantly larger dataset and a novel architecture that expands beyond the current LLaVA method.