add cpu branch

app.py

@@ -28,6 +28,11 @@ def predict(
 
     instruction += f"<|im_start|>user\n{message}\n<|im_end|>\n<|im_start|>assistant\n"
     try:
+        if device == torch.device("cpu"):
+            raise EnvironmentError(
+                "If you have computing power, you can test by cloning to local or forking to an account with purchased GPU environment"
+            )
+
         streamer = TextIteratorStreamer(
             tokenizer,
             skip_prompt=True,
@@ -67,8 +72,10 @@ def predict(
 
 if __name__ == "__main__":
     device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-    tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
-    model = AutoModelForCausalLM.from_pretrained(MODEL_ID, device_map="auto")
+    if device == torch.device("cuda"):
+        tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+        model = AutoModelForCausalLM.from_pretrained(MODEL_ID, device_map="auto")
+
     # Create Gradio interface
     gr.ChatInterface(
         predict,