From df6e303fd39ccd94a0e55c501fcaccd1065ee34e Mon Sep 17 00:00:00 2001
From: LostRuins Concedo <39025047+LostRuins@users.noreply.github.com>
Date: Mon, 10 Nov 2025 11:24:04 +0800
Subject: [PATCH] merge https://github.com/ggml-org/llama.cpp/pull/17128

---
 tools/mtmd/clip.cpp | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/tools/mtmd/clip.cpp b/tools/mtmd/clip.cpp
index c6c4a7f6d..6da4835e9 100644
--- a/tools/mtmd/clip.cpp
+++ b/tools/mtmd/clip.cpp
@@ -182,13 +182,13 @@ enum patch_merge_type {
 };
 
 struct clip_hparams {
-    int32_t image_size;
-    int32_t patch_size;
-    int32_t n_embd;
-    int32_t n_ff;
-    int32_t projection_dim;
-    int32_t n_head;
-    int32_t n_layer;
+    int32_t image_size = 0;
+    int32_t patch_size = 0;
+    int32_t n_embd = 0;
+    int32_t n_ff = 0;
+    int32_t projection_dim = 0;
+    int32_t n_head = 0;
+    int32_t n_layer = 0;
     // idefics3
     int32_t image_longest_edge = 0;
     int32_t image_min_pixels = -1;
@@ -2728,6 +2728,9 @@ struct clip_model_loader {
                 }
             } else if (is_audio) {
                 get_u32(KEY_A_NUM_MEL_BINS, hparams.n_mel_bins);
+                // some hparams are unused, but still need to set to avoid issues
+                hparams.image_size = 0;
+                hparams.patch_size = 1;
 
             } else {
                 GGML_ASSERT(false && "unknown modality");