Update app.py

app.py

@@ -4,19 +4,20 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import transformers
 import torch
 
+model = "tiiuae/falcon-7b"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    torch_dtype=torch.bfloat16,
+    trust_remote_code=True,
+    device_map="auto",
+)
 
 def falcon(input_text):
-    model = "tiiuae/falcon-40b"
 
-    tokenizer = AutoTokenizer.from_pretrained(model)
-    pipeline = transformers.pipeline(
-        "text-generation",
-        model=model,
-        tokenizer=tokenizer,
-        torch_dtype=torch.bfloat16,
-        trust_remote_code=True,
-        device_map="auto",
-    )
     sequences = pipeline(
         input_text, # "Was ist das höchste Gebäude in der Welt?"
         max_length=200,