.

app.py

@@ -37,7 +37,7 @@ def fn(uploaded_file) -> str:
 
     # Generate text based on the context
     context = prepare_context(data)
-    generated_text = pipeline('text-generation', model=model)(context)[0]['generated_text']
+    generated_text = pipeline('text-generation', model=peft_model)(context)[0]['generated_text']
     ret += generated_text
 
     # Internally prompt the model to data analyze the EHR patient data
@@ -48,7 +48,7 @@ def fn(uploaded_file) -> str:
         input_ids = tokenizer.encode(prompt, return_tensors="pt")
 
         # Generate text based on the prompt
-        generated_text = pipeline('text-generation', model=model)(input_ids=input_ids)[0]['generated_text']
+        generated_text = pipeline('text-generation', model=peft_model)(input_ids=input_ids)[0]['generated_text']
         ret += generated_text
 
     return ret