From 3e2597eac888e6e12c7bc7021016ca5104db83ba Mon Sep 17 00:00:00 2001
From: Andrei Betlen <abetlen@gmail.com>
Date: Sun, 5 May 2024 12:12:27 -0400
Subject: [PATCH] feat: Update llama.cpp

---
 llama_cpp/llama_cpp.py | 6 +++++-
 vendor/llama.cpp       | 2 +-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/llama_cpp/llama_cpp.py b/llama_cpp/llama_cpp.py
index 46aa516..9e934e0 100644
--- a/llama_cpp/llama_cpp.py
+++ b/llama_cpp/llama_cpp.py
@@ -294,6 +294,8 @@ LLAMA_VOCAB_TYPE_WPM = 3
 #     LLAMA_VOCAB_PRE_TYPE_MPT            = 5,
 #     LLAMA_VOCAB_PRE_TYPE_STARCODER      = 6,
 #     LLAMA_VOCAB_PRE_TYPE_GPT2           = 7,
+#     LLAMA_VOCAB_PRE_TYPE_REFACT         = 8,
+#     LLAMA_VOCAB_PRE_TYPE_COMMAND_R      = 9,
 # };
 LLAMA_VOCAB_PRE_TYPE_DEFAULT = 0
 LLAMA_VOCAB_PRE_TYPE_LLAMA3 = 1
@@ -303,6 +305,8 @@ LLAMA_VOCAB_PRE_TYPE_FALCON = 4
 LLAMA_VOCAB_PRE_TYPE_MPT = 5
 LLAMA_VOCAB_PRE_TYPE_STARCODER = 6
 LLAMA_VOCAB_PRE_TYPE_GPT2 = 7
+LLAMA_VOCAB_PRE_TYPE_REFACT = 8
+LLAMA_VOCAB_PRE_TYPE_COMMAND_R = 9
 
 
 # // note: these values should be synchronized with ggml_rope
@@ -494,7 +498,7 @@ class llama_token_data_array(ctypes.Structure):
 
 llama_token_data_array_p = ctypes.POINTER(llama_token_data_array)
 
-# typedef bool (*llama_progress_callback)(float progress, void *ctx);
+# typedef bool (*llama_progress_callback)(float progress, void * user_data);
 llama_progress_callback = ctypes.CFUNCTYPE(
     ctypes.c_bool, ctypes.c_float, ctypes.c_void_p
 )
diff --git a/vendor/llama.cpp b/vendor/llama.cpp
index 6ecf318..628b299 160000
--- a/vendor/llama.cpp
+++ b/vendor/llama.cpp
@@ -1 +1 @@
-Subproject commit 6ecf3189e00a1e8e737a78b6d10e1d7006e050a2
+Subproject commit 628b299106d1e9476fdecb3cbe546bf5c60f1b89