Update app.py

app.py

@@ -1,12 +1,12 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+#from huggingface_hub import InferenceClient
 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
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 
 model, tokenizer = FastLanguageModel.from_pretrained(
@@ -38,7 +38,8 @@ def texto_Patol(input):
           "", # input
           "", # output - leave this blank for generation!
       )
-  ], return_tensors = "pt").to("cuda")
+  ], return_tensors = "pt")
+#.to("cuda")
 
   outputs = model.generate(**inputs, max_new_tokens = 2048, use_cache = True)
   return tokenizer.batch_decode(outputs)