correct llama_chat_apply_template function params

JamePeng · JamePeng · commit 7ddf097ca6f3 · 2025-01-26T23:52:10.000+08:00
diff --git a/llama_cpp/llama_cpp.py b/llama_cpp/llama_cpp.py
@@ -2942,19 +2942,17 @@ def llama_detokenize(
 # // Chat templates
 # //
 
-
 # /// Apply chat template. Inspired by hf apply_chat_template() on python.
 # /// Both "model" and "custom_template" are optional, but at least one is required. "custom_template" has higher precedence than "model"
 # /// NOTE: This function does not use a jinja parser. It only support a pre-defined list of template. See more: https://github.com/ggerganov/llama.cpp/wiki/Templates-supported-by-llama_chat_apply_template
-# /// @param tmpl A Jinja template to use for this chat. If this is nullptr, the model’s default chat template will be used instead.
+# /// @param tmpl A Jinja template to use for this chat. If this is nullptr, the model's default chat template will be used instead.
 # /// @param chat Pointer to a list of multiple llama_chat_message
 # /// @param n_msg Number of llama_chat_message in this chat
 # /// @param add_ass Whether to end the prompt with the token(s) that indicate the start of an assistant message.
 # /// @param buf A buffer to hold the output formatted prompt. The recommended alloc size is 2 * (total number of characters of all messages)
 # /// @param length The size of the allocated buffer
 # /// @return The total number of bytes of the formatted prompt. If is it larger than the size of buffer, you may need to re-alloc it and then re-apply the template.
 # LLAMA_API int32_t llama_chat_apply_template(
-#           const struct llama_model * model,
 #                         const char * tmpl,
 #    const struct llama_chat_message * chat,
 #                             size_t   n_msg,
@@ -2964,18 +2962,22 @@ def llama_detokenize(
 @ctypes_function(
     "llama_chat_apply_template",
     [
-        ctypes.c_void_p,
         ctypes.c_char_p,
         ctypes.POINTER(llama_chat_message),
         ctypes.c_size_t,
+        bool,
+        ctypes.c_char_p,
+        ctypes.c_int32
     ],
     ctypes.c_int32,
 )
 def llama_chat_apply_template(
-    model: llama_model_p,
     tmpl: bytes,
     chat: CtypesArray[llama_chat_message],
     n_msg: int,
+    add_ass: bool,
+    buf: bytes,
+    length: int,
     /,
 ) -> int:
     ...
