Add pipeline_tag and library_name to model card

This PR enhances the model card by adding key metadata tags:
- `pipeline_tag: text-generation`: This allows the model to be easily discoverable through the text-generation filter on the Hub and accurately reflects its primary function of generating examination results.
- `library_name: transformers`: This enables the "how to use" widget on the model page, providing automated code snippets for users, as the model is compatible with the `transformers` library as demonstrated in the "Quickstart" section.

These additions will improve the usability and visibility of the model on the Hugging Face Hub.

README.md

@@ -1,10 +1,13 @@
 ---
-license: apache-2.0
-language:
-- en
 base_model:
 - Qwen/Qwen2.5-7B-Instruct
+language:
+- en
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
 ---
+
 # DiagGym: Virtual Clinical Environment (EHR World Model)
 
 
@@ -59,16 +62,27 @@ class DiagGym:
 
     def simulate(self, context: str, past_events_list: list, exam_name: str) -> Optional[str]:
         """Generate exam results based on patient context and past events."""
-        context += "\nThe following summarizes the results from the patient's medical examination:\n"
+        context += "
+The following summarizes the results from the patient's medical examination:
+"
         
         if len(past_events_list) == 0:
-            input_prompt = context + "Exam name:\n" + exam_name + "\nExam results:\n"
+            input_prompt = context + "Exam name:
+" + exam_name + "
+Exam results:
+"
         else:
             past_events_str = [
-                f"Exam name:\n{event_name}\nExam results:\n{resp}"
+                f"Exam name:
+{event_name}
+Exam results:
+{resp}"
                 for (event_name, resp) in past_events_list
             ]
-            input_prompt = context + SEP.join(past_events_str) + SEP + "Exam name:\n" + exam_name + "\nExam results:\n"
+            input_prompt = context + SEP.join(past_events_str) + SEP + "Exam name:
+" + exam_name + "
+Exam results:
+"
         
         response = self.client.completions.create(
             model=self.model_name_or_path,
@@ -110,19 +124,32 @@ exam_name = "CHEST (PORTABLE AP)"
 if len(past_events_list) == 0:
     prompt = (
         context
-        + "\nThe following summarizes the results from the patient's medical examination:\n"
-        + "Exam name:\n" + exam_name + "\nExam results:\n"
+        + "
+The following summarizes the results from the patient's medical examination:
+"
+        + "Exam name:
+" + exam_name + "
+Exam results:
+"
     )
 else:
     past_events_str = [
-        f"Exam name:\n{event_name}\nExam results:\n{resp}"
+        f"Exam name:
+{event_name}
+Exam results:
+{resp}"
         for (event_name, resp) in past_events_list
     ]
     prompt = (
         context
-        + "\nThe following summarizes the results from the patient's medical examination:\n"
+        + "
+The following summarizes the results from the patient's medical examination:
+"
         + SEP.join(past_events_str) + SEP
-        + "Exam name:\n" + exam_name + "\nExam results:\n"
+        + "Exam name:
+" + exam_name + "
+Exam results:
+"
     )
 
 inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
@@ -189,4 +216,4 @@ On 863 MIMIC‑IV cases, DiagGym shows strong step‑level similarity and full
 ## Contact
 
 - For implementation detailes, please refer to our GitHub: https://github.com/MAGIC-AI4Med/DiagGym
-- Email: henrychur@sjtu.edu.cn
+- Email: henrychur@sjtu.edu.cn