Update app.py

app.py

@@ -5,11 +5,19 @@ from gpt4all import GPT4All
 model_path = "pytorch_model-00001-of-00002.bin"
 
 # Initialize the GPT4All model
-model = GPT4All(model_path)
+# model = GPT4All(model_path
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    quantization_config=bnb_config,
+    device_map=device_map
+)
 
 def generate_text(input_text):
-    output = model.generate(input_text)
-    return output
+    # output = model.generate(input_text)
+    # return output
+    pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
+    result = pipe(f"<s>[INST] {prompt} [/INST]")
+    return result
 
 text_generation_interface = gr.Interface(
     fn=generate_text,