From b8ac9ba752544f0362aa6013cd602a109065bb4f Mon Sep 17 00:00:00 2001
From: fxmarty <9808326+fxmarty@users.noreply.github.com>
Date: Fri, 7 Jun 2024 12:43:33 +0000
Subject: [PATCH] precise comment

---
 server/text_generation_server/models/__init__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/server/text_generation_server/models/__init__.py b/server/text_generation_server/models/__init__.py
index 53bf8855..2e7e83a0 100644
--- a/server/text_generation_server/models/__init__.py
+++ b/server/text_generation_server/models/__init__.py
@@ -420,7 +420,7 @@ def get_model(
         and max_input_tokens > sliding_window
     ):
         raise ValueError(
-            f"The backend {SYSTEM} does not support sliding window attention. TGI webserver was started max_input_tokens={max_input_tokens} larger than sliding_window={sliding_window}. To use this model with the {SYSTEM} backend, please launch TGI with the argument `--max-batch-prefill-tokens` smaller than {sliding_window}."
+            f"The backend {SYSTEM} does not support sliding window attention that is used by the model type {model_type}. To use this model nonetheless with the {SYSTEM} backend, please launch TGI with the argument `--max-input-tokens` smaller than sliding_window={sliding_window} (got here max_input_tokens={max_input_tokens})."
         )
 
     if model_type == MAMBA: