Update app.py

app.py

@@ -8,25 +8,23 @@ import pytesseract as tess
 from sentence_transformers import SentenceTransformer, util
 import io
 
-model_name = "eachadea/vicuna-7b-1.1"
+save_directory="Garvitj/grader"
 
-# Check if CUDA is available, otherwise, fall back to CPU
-device = "cuda" if torch.cuda.is_available() else "cpu"
-print(f"Using device: {device}")
+# Load the tokenizer from the saved directory
+tokenizer = AutoTokenizer.from_pretrained(save_directory)
 
-# Load the tokenizer
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-# Load the model
-# If CUDA is available, use float16, otherwise, use float32
+# Load the model from the saved directory
 model = AutoModelForCausalLM.from_pretrained(
-    model_name, 
+    save_directory,
     torch_dtype=torch.float16 if device == "cuda" else torch.float32,
     device_map="auto" if device == "cuda" else None
 )
 
 # Move model to the appropriate device (CPU or CUDA)
 model.to(device)
+
+print(f"Model and tokenizer loaded from {save_directory}")
+
 tess.pytesseract.tesseract_cmd = r"/app/tesseract.exe"
 # Load a smaller version of Sentence-BERT model
 model1 = SentenceTransformer('all-MiniLM-L6-v2')