wip

app.py

@@ -15,6 +15,12 @@ model.load_adapter(model_id,device_map="auto")
 
 def infere(image):
     messages = [
+        {
+        "role": "system",
+        "content": [
+            {"type": "text", "text": "You are a valuable medical doctor and you are looking at an image of your patient."},
+        ]
+        },
     {
         "role": "user",
         "content": [
@@ -25,9 +31,9 @@ def infere(image):
     ]
     prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
     inputs = processor(text=prompt, images=[image], return_tensors="pt")
-    print(f"inputs: {inputs}")
+    # print(f"inputs: {inputs}")
     inputs = {k: v.to(device) for k, v in inputs.items()}
-    generated_ids = model.generate(**inputs, max_new_tokens=8192)
+    generated_ids = model.generate(**inputs, max_new_tokens=100)
     generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
     return generated_texts