🌘w🌖

app.py

@@ -8,7 +8,7 @@ import torch
 from threading import Thread
 from sentence_transformers import SentenceTransformer
 from datasets import load_dataset
-
+import time
 
 token = os.environ["HF_TOKEN"]
 model = AutoModelForCausalLM.from_pretrained(
@@ -96,7 +96,7 @@ def talk(message, history):
     print("initializing thread ...")
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()
-
+    time.sleep(1)
     # Initialize an empty string to store the generated text
     partial_text = ""
     for new_text in streamer: