Update README.md

README.md

@@ -21,15 +21,11 @@ pipeline_tag: image-text-to-text
 
 We train and release "Cerule", a tiny yet powerful Vision Lanuage Model based on the newly released Google's [Gemma-2b](https://huggingface.co/google/gemma-2b) and Google's [SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384). 
 
-We utilise highly efficient data selection techniques with:
 ```
 - Pretraining stage : 650K images (A LAION Subset)
-- Finetuning stage : 695K images (SVIT-mix-665K modified for finetuning(Dataset SOON!))
+- Finetuning stage : 695K images (SVIT-mix-665K - Bunny mix modified by BAAI)
 ```
-The training setup was `4xA100's 80GB` and took ~6 hours to pretrain and ~13 hours to finetune. We modify and adapt the training code from [LLaVA](https://github.com/haotian-liu/LLaVA). 
-
-🚨 Training code, Data and more details to release soon!
-
+The training setup was `4xA100's 80GB` and took ~6 hours to pretrain and ~13 hours to finetune. We modify and adapt the training code from [Bunny](https://github.com/BAAI-DCAI/Bunny). 
 
 ---
 | Image | Example |