llama : add <|tool_call|> formatting to Granite template (ggml-org#10177)

Branch: GraniteToolCallTemplate

Signed-off-by: Gabe Goodhart <[email protected]>

Author: gabe-l-hart

src/llama.cpp

@@ -21808,8 +21808,11 @@ static int32_t llama_chat_apply_template_internal(
         // IBM Granite template
         for (const auto & message : chat) {
             std::string role(message->role);
-            ss << "<|start_of_role|>" << role << "<|end_of_role|>"
-               << message->content << "<|end_of_text|>\n";
+            ss << "<|start_of_role|>" << role << "<|end_of_role|>";
+            if (role == "assistant_tool_call") {
+                ss << "<|tool_call|>";
+            }
+            ss << message->content << "<|end_of_text|>\n";
         }
         if (add_ass) {
             ss << "<|start_of_role|>assistant<|end_of_role|>\n";