From 656af41b5d24520f37ceec5147ba36c3ae469f01 Mon Sep 17 00:00:00 2001
From: kingbri <8082010+kingbri1@users.noreply.github.com>
Date: Fri, 9 May 2025 22:25:50 -0400
Subject: [PATCH] Model: Always enable decode_special_tokens

The frontend should handle the special tokens if they get emitted.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
---
 backends/exllamav2/model.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/backends/exllamav2/model.py b/backends/exllamav2/model.py
index c2a084b..65689f4 100644
--- a/backends/exllamav2/model.py
+++ b/backends/exllamav2/model.py
@@ -1373,6 +1373,7 @@ class ExllamaV2Container(BaseModelContainer):
             min_new_tokens=params.min_tokens,
             gen_settings=gen_settings,
             stop_conditions=stop_conditions,
+            decode_special_tokens=True,
             filters=grammar_handler.filters,
             filter_prefer_eos=bool(grammar_handler.filters),
             return_probs=params.logprobs > 0,