runtime error

Exit code: 1. Reason: ing ... sched_reserve: Flash Attention was auto, set to enabled sched_reserve: resolving fused Gated Delta Net support: sched_reserve: fused Gated Delta Net (autoregressive) enabled sched_reserve: fused Gated Delta Net (chunked) enabled sched_reserve: CPU compute buffer size = 522.00 MiB sched_reserve: graph nodes = 1867 sched_reserve: graph splits = 1 sched_reserve: reserve took 8.73 ms, sched copies = 1 common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable) clip_model_loader: model name: clip_model_loader: description: clip_model_loader: GGUF version: 3 clip_model_loader: alignment: 32 clip_model_loader: n_tensors: 1411 clip_model_loader: n_kv: 32 clip_model_loader: has vision encoder clip_model_loader: has audio encoder clip_ctx: CLIP using CPU backend load_hparams: projector: gemma4v load_hparams: n_embd: 768 load_hparams: n_head: 12 load_hparams: n_ff: 3072 load_hparams: n_layer: 16 load_hparams: ffn_op: gelu_quick load_hparams: projection_dim: 1536 --- vision hparams --- load_hparams: image_size: 224 load_hparams: patch_size: 16 load_hparams: has_llava_proj: 0 load_hparams: minicpmv_version: 0 load_hparams: n_merge: 3 load_hparams: n_wa_pattern: 0 load_hparams: image_min_pixels: 580608 load_hparams: image_max_pixels: 645120 load_hparams: model size: 939.89 MiB load_hparams: metadata size: 0.50 MiB warmup: warmup with image size = 768 x 768 alloc_compute_meta: CPU compute buffer size = 94.52 MiB alloc_compute_meta: graph splits = 1, nodes = 940 warmup: flash attention is enabled mtmd_init_from_file: error: mismatch between text model (n_embd = 2560) and mmproj (n_embd = 1536) hint: you may be using wrong mmproj srv load_model: failed to load multimodal model, '/mmproj-gemma-4-e2b-it-f16.gguf' srv operator(): operator(): cleaning up before exit... main: exiting due to model loading error

Container logs: