Spaces:

lapa-llm
/

lapa

Running on Zero

robinhad commited on Aug 26

Commit

1e3f8c3

verified ·

1 Parent(s): 3c3f8d4

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -49,7 +49,7 @@ def respond(
         add_generation_prompt=True,
         enable_thinking=True,
     )
-    # input_text += "<think>" # TODO: remove short term fix
     print(input_text)
     inputs = tokenizer(input_text, return_tensors="pt").to(model.device) # .to(device)

         add_generation_prompt=True,
         enable_thinking=True,
     )
+    input_text += "<think>" # TODO: remove short term fix
     print(input_text)
     inputs = tokenizer(input_text, return_tensors="pt").to(model.device) # .to(device)