Update app.py

app.py

@@ -21,7 +21,7 @@ model = AutoModelForCausalLM.from_pretrained(
 ).to(device)
 @spaces.GPU(enable_queue=True)
 def generate_text(text, temperature, maxLen):
-    text = text.strip().strip('<s>').strip()
+    text = text.lstrip().lstrip('<s>').lstrip()
     inputs = tokenizer([text], return_tensors="pt").to(device)
     streamer = TextIteratorStreamer(tokenizer)
     generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=maxLen, temperature=temperature)
@@ -31,6 +31,7 @@ def generate_text(text, temperature, maxLen):
     toks = 0
     for out in streamer:
         t += out
+        t = t.lstrip().lstrip('<s>').lstrip()
         yield t
 with gr.Blocks(theme=theme) as demo:
     gr.Markdown("""