Update README.md

README.md

@@ -3,8 +3,9 @@ language: en
 license: mit
 tags:
 - vision
-- image-to-text
 model_name: microsoft/git-base-textvqa
+inference: false
+pipeline_tag: visual-question-answering
 ---
 
 # GIT (GenerativeImage2Text), base-sized, fine-tuned on TextVQA
@@ -63,4 +64,4 @@ During validation, one resizes the shorter edge of each image, after which cente
 
 ## Evaluation results
 
-For evaluation results, we refer readers to the [paper](https://arxiv.org/abs/2205.14100).
+For evaluation results, we refer readers to the [paper](https://arxiv.org/abs/2205.14100).