Update README.md

README.md

@@ -24,8 +24,8 @@ model-index:
           type: image-to-text
           name: Image To Text
         dataset:
-          name: nlphuji/flickr30k
-          type: nlphuji/flickr30k
+          name: Mozilla/flickr30k-transformed-captions
+          type: Mozilla/flickr30k-transformed-captions
         metrics:
           - name: ROUGE-1
             type: rouge
@@ -68,14 +68,11 @@ You can get that checkpoint using the 3083a3cef6e3c8dd90df3f088074bbe836b0f403 c
 
 It was then further fine-tuned on :
 
-- Flickr30k debiased: https://huggingface.co/datasets/Mozilla/flickr30k-transformed-captions
-- DocOrNot: https://huggingface.co/datasets/Mozilla/docornot
+- [Flickr30k debiased](https://huggingface.co/datasets/Mozilla/flickr30k-transformed-captions)
+- [DocOrNot](https://huggingface.co/datasets/Mozilla/docornot)
+- [Alt Text Validation](https://huggingface.co/datasets/Mozilla/alt-text-validation)
 
-You can find the code used to create the model here: https://github.com/mozilla/distilvit
+For the latter, the dataset was annotated by our team to correct the alt text generated by the model,
+using the [checkvite tool](https://github.com/mozila/checkvite).
 
-### Framework versions
-
-- Transformers 4.40.2
-- Pytorch 2.3.0+cu121
-- Datasets 2.19.1
-- Tokenizers 0.19.1
+You can find the code used to create the model here: https://github.com/mozilla/distilvit