Update

app.py

@@ -1,3 +1,4 @@
+import os
 from threading import Thread
 from typing import Iterator
 
@@ -8,7 +9,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 
 MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
-MAX_INPUT_TOKEN_LENGTH = 4096
+MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 DESCRIPTION = """\
 # Llama-2 7B Chat