From 6298f49816c2264f9bb77206ad1b015aa357e381 Mon Sep 17 00:00:00 2001
From: Daniel Hiltgen <daniel@ollama.com>
Date: Wed, 3 Jul 2024 12:37:40 -0700
Subject: [PATCH] Fix clip model loading with unicode paths

On windows, if the model dir contained unicode characters
clip models would fail to load.  This fixes the file name
handling in clip.cpp to support utf16 on windows.
---
 llm/patches/08-clip-unicode.diff | 42 ++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)
 create mode 100644 llm/patches/08-clip-unicode.diff

diff --git a/llm/patches/08-clip-unicode.diff b/llm/patches/08-clip-unicode.diff
new file mode 100644
index 00000000..53e5ee11
--- /dev/null
+++ b/llm/patches/08-clip-unicode.diff
@@ -0,0 +1,42 @@
+diff --git a/examples/llava/clip.cpp b/examples/llava/clip.cpp
+index 95fbe3d0..5a02a6ec 100644
+--- a/examples/llava/clip.cpp
++++ b/examples/llava/clip.cpp
+@@ -32,6 +33,14 @@
+ #include <cinttypes>
+ #include <limits>
+ 
++#if defined(_WIN32)
++#define WIN32_LEAN_AND_MEAN
++#ifndef NOMINMAX
++    #define NOMINMAX
++#endif
++#include <windows.h>
++#endif
++
+ //#define CLIP_DEBUG_FUNCTIONS
+ 
+ // RGB uint8 image
+@@ -1055,7 +1064,22 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {
+             return nullptr;
+         }
+ 
++#ifdef _WIN32
++        int wlen = MultiByteToWideChar(CP_UTF8, 0, fname, -1, NULL, 0);
++        if (!wlen) {
++            return NULL;
++        }
++        wchar_t * wbuf = (wchar_t *) malloc(wlen * sizeof(wchar_t));
++        wlen = MultiByteToWideChar(CP_UTF8, 0, fname, -1, wbuf, wlen);
++        if (!wlen) {
++            free(wbuf);
++            return NULL;
++        }
++        auto fin = std::ifstream(wbuf, std::ios::binary);
++        free(wbuf);
++#else
+         auto fin = std::ifstream(fname, std::ios::binary);
++#endif
+         if (!fin) {
+             LOG_TEE("cannot open model file for loading tensors\n");
+             clip_free(new_clip);