diff --git a/aio/cpu/text-to-text.yaml b/aio/cpu/text-to-text.yaml
index aeb3c8426..d30f403ed 100644
--- a/aio/cpu/text-to-text.yaml
+++ b/aio/cpu/text-to-text.yaml
@@ -41,6 +41,7 @@ f16: true
 stopwords:
 - <|im_end|>
 - <dummy32000>
+- "\n</tool_call>"
 usage: |
       curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
           "model": "gpt-4",
diff --git a/aio/gpu-8g/text-to-text.yaml b/aio/gpu-8g/text-to-text.yaml
index 1a67169b6..1645a2573 100644
--- a/aio/gpu-8g/text-to-text.yaml
+++ b/aio/gpu-8g/text-to-text.yaml
@@ -41,6 +41,7 @@ f16: true
 stopwords:
 - <|im_end|>
 - <dummy32000>
+- "\n</tool_call>"
 usage: |
       curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
           "model": "gpt-4",
diff --git a/aio/intel/text-to-text.yaml b/aio/intel/text-to-text.yaml
index 0577d19b1..3f3d2c39c 100644
--- a/aio/intel/text-to-text.yaml
+++ b/aio/intel/text-to-text.yaml
@@ -40,6 +40,7 @@ template:
 context_size: 4096
 stopwords:
 - <|im_end|>
+- "\n</tool_call>"
 - <dummy32000>
 usage: |
       curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
diff --git a/embedded/models/hermes-2-pro-mistral.yaml b/embedded/models/hermes-2-pro-mistral.yaml
index 108216f5c..3792be78b 100644
--- a/embedded/models/hermes-2-pro-mistral.yaml
+++ b/embedded/models/hermes-2-pro-mistral.yaml
@@ -41,6 +41,7 @@ f16: true
 stopwords:
 - <|im_end|>
 - <dummy32000>
+- "\n</tool_call>"
 usage: |
       curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
           "model": "hermes-2-pro-mistral",