fixed err

app.py

@@ -7,9 +7,12 @@ with init_empty_weights():
     tokenizer = AutoTokenizer.from_pretrained("Cognitive-Lab/LLama3-Gaja-Hindi-8B-v0.1")
     model = AutoModelForCausalLM.from_pretrained("Cognitive-Lab/LLama3-Gaja-Hindi-8B-v0.1")
 
+# Load the model weights after initialization
+model.load_state_dict(torch.load("path/to/your/model/pytorch_model.bin"))
+
 # Move the model to the GPU if available; otherwise, keep it on the CPU
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model = model.to(device)
+model.to(device)
 
 # Define a function to run inference
 def generate_response(prompt, max_new_tokens=30):