Update app.py

app.py

@@ -1,17 +1,15 @@
 import requests
 import torch
 from PIL import Image
-from transformers import LlamaForConditionalGeneration, AutoProcessor
+from transformers import pipeline
 
-# Define the model ID, replace with the correct ID if needed
-model_id = "meta-llama/Llama-3.2-11B-Vision-Instruct"
+pipe = pipeline("text-generation", model="meta-llama/Llama-3.2-1B")
 
-# Load the model in bfloat16 or float16 if needed
-model = LlamaForConditionalGeneration.from_pretrained(
-    model_id,
-    torch_dtype=torch.bfloat16,  # Change to torch.float16 if hardware doesn't support bfloat16
-    device_map="auto",  # Automatically selects the appropriate device
-)
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B")
 
 # Load the processor
 processor = AutoProcessor.from_pretrained(model_id)