meta-llama

app.py

@@ -20,7 +20,7 @@ print(f"Low memory mode: {LOW_MEMORY}")
 HF_TOKEN = os.environ.get('HF_TOKEN')
 
 # Load the model and processor
-model_name = "ruslanmv/Llama-3.2-11B-Vision-Instruct"
+model_name = "meta-llama/Llama-3.2-11B-Vision-Instruct"
 model = MllamaForConditionalGeneration.from_pretrained(
     model_name,
     use_auth_token=HF_TOKEN,
@@ -37,7 +37,7 @@ def predict(image, text):
     # Prepare the input messages
     messages = [
         {"role": "user", "content": [
-           # {"type": "image"},  # Specify that an image is provided
+            {"type": "image"},  # Specify that an image is provided
             {"type": "text", "text": text}  # Add the user-provided text input
         ]}
     ]
@@ -46,7 +46,7 @@ def predict(image, text):
     input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
     
     # Process the inputs and move to the appropriate device
-    inputs = processor(input_text, return_tensors="pt").to(device)
+    inputs = processor(image, input_text, return_tensors="pt").to(device)
     
     # Generate a response from the model
     outputs = model.generate(**inputs, max_new_tokens=100)