Update app.py

app.py

@@ -7,8 +7,6 @@ import os
 import time
 
 
-
-
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
 MODEL_ID = "CohereForAI/aya-23-8B"
 MODEL_NAME = MODEL_ID.split("/")[-1]
@@ -74,7 +72,11 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
         temperature=temperature,
     )
 
-    gen_text = tokenizer.decode(gen_tokens[0])
+    gen_tokens = [
+      gt[prompt_padded_len:] for gt in gen_tokens
+    ]
+
+    gen_text = tokenizer.batch_decode(gen_tokens, skip_special_tokens=True)
 
     return gen_text