Skip to content

mtmd: fix patch_size initialized to random value in audio models #17128

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
+10 −7
Open

mtmd: fix patch_size initialized to random value in audio models #17128

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1fffbd3
mtmd: fix patch_size initialized to random value in audio models
ngxson Nov 9, 2025
4ac2c20
add default hparams
ngxson Nov 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 10 additions & 7 deletions tools/mtmd/clip.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,13 +160,13 @@ 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;
Expand Down Expand Up @@ -2683,6 +2683,9 @@ 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");
Expand Down
Loading