work?

app.py

@@ -1,18 +1,19 @@
 import gradio as gr
-from transformers import pipeline
+#from transformers import pipeline
 #from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("kolbeins/model")
+model = AutoModelForCausalLM.from_pretrained("kolbeins/model")
 
-#model = AutoModel.from_pretrained("kolbeins/model")  
-pipeline = pipeline(task="text-generation", model="kolbeins/model")
-#model = AutoModelForCausalLM.from_pretrained("kolbeins/model")
-#tokenizer = AutoTokenizer.from_pretrained("kolbeins/model")
 
 def chat(input_txt):
-    response = pipeline(input_txt)
-    #inputs = tokenizer(input_txt, return_tensors="pt")
-    #outputs = model.generate(inputs["input_ids"], max_length=150, num_return_sequences=1)
-    #response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    inputs = tokenizer(input_txt, return_tensors="pt")
+    outputs = model.generate(**inputs)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return response
 
+
+
 demo = gr.Interface(fn=chat, inputs="text", outputs="text")
 demo.launch(share=True)