diff --git a/tools/mtmd/clip.cpp b/tools/mtmd/clip.cpp index 767ad9f79..d723432a7 100644 --- a/tools/mtmd/clip.cpp +++ b/tools/mtmd/clip.cpp @@ -1842,6 +1842,7 @@ struct clip_model_loader { log_ffn_op = "gelu"; hparams.n_merge = 3; // pooling_kernel_size hparams.image_resize_algo = RESIZE_ALGO_BICUBIC; + hparams.image_resize_pad = PAD_NONE; get_u32(KEY_PROJ_SCALE_FACTOR, hparams.n_merge, false); if (model.proj_type == PROJECTOR_TYPE_GEMMA4UV) { // for "unified" variant, we directly use a bigger patch size, because the "token merging" is done directly on conv layer