Update app.py

app.py

@@ -20,7 +20,7 @@ embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
 vectordb = FAISS.from_documents(split_docs, embeddings)
 
 # Load model and create pipeline
-model_name = "01-ai/Yi-Coder-9B"
+model_name = "Qwen/Qwen2.5-Coder-3B-Instruct"
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 print(f"Using device: {device}")
@@ -30,7 +30,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(
     model_name, 
     device_map=device,
-    torch_dtype=torch.float16 if device == "cuda" else torch.float32
+    torch_dtype=torch.float32 if device == "cuda" else torch.float32
 )
 #model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto")
 qa_pipeline = pipeline(