bypass cuda

app.py

@@ -2,7 +2,9 @@ import gradio as gr
 # from huggingface_hub import InferenceClient
 # from peft import AutoPeftModelForCausalLM
 # from transformers import AutoTokenizer, TextStreamer, BitsAndBytesConfig
-from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
+# from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
+import os
+os.environ["CUDA_VISIBLE_DEVICES"] = ""
 from unsloth import FastLanguageModel
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference