Improve model card: Add library_name and correct pipeline_tag

This PR improves the model card by:

- Correcting the `pipeline_tag` to `image-text-to-text` to accurately reflect the model's functionality.
- Adding the `library_name` to the metadata for improved discoverability.

README.md

@@ -1,14 +1,16 @@
 ---
-license: cc-by-nc-4.0
 language:
 - en
-pipeline_tag: zero-shot-image-classification
+license: cc-by-nc-4.0
+pipeline_tag: image-text-to-text
+library_name: transformers
 tags:
 - medical
 - multimodal
 - vision-language pre-training
 - chest x-ray
 ---
+
 # MeDSLIP: Medical Dual-Stream Language-Image Pre-training for Fine-grained Alignment
 
 ## Introduction:
@@ -44,7 +46,7 @@ All files for data preparation files can be downloaded from [Hugging Face: MeDSL
 ### Pre-training
 Our pre-train code is given in ```PreTrain_MeDSLIP```.
 * Check the ```PreTrain_MeDSLIP/data_file``` dir and download the files for data preparation.
-* Change the data and preparation files paths as you disire in ```PreTrain_MeDSLIP/configs/Pretrain_MeDSLIP.yaml```, and ```python PreTrain_MeDSLIP/train_MeDSLIP.py``` to pre-train.
+* Change the data and preparation files paths as you desire in ```PreTrain_MeDSLIP/configs/Pretrain_MeDSLIP.yaml```, and ```python PreTrain_MeDSLIP/train_MeDSLIP.py``` to pre-train.
 
 ## Reference
 ```