Add requirements.txt

app.py

@@ -1,5 +1,7 @@
 import re
 
+import torch
+
 import gradio as gr
 
 from peft import PeftModel
@@ -84,7 +86,8 @@ def response(user_schemas, user_question):
                                            return_dict=True,
                                            return_tensors="pt")
     
-    outputs = model.generate(**inputs, max_new_tokens=1024)
+    with torch.inference_mode():
+        outputs = model.generate(**inputs, max_new_tokens=1024)
     
     outputs = tokenizer.batch_decode(outputs)
     output = outputs[0].split("<|im_start|>assistant")[-1]

requirements.txt

@@ -0,0 +1,3 @@
+torch
+peft
+gradio