LLM inference in C/C++
C++ ggml
models : fix mimo2 swa pattern load (#28865)
Sigbjørn Skjæret1aca1f9fcd23
diff --git a/src/models/mimo2.cpp b/src/models/mimo2.cppindex 8772319f46..a466984af0 100644--- a/src/models/mimo2.cpp+++ b/src/models/mimo2.cpp@@ -9,7 +9,7 @@ void llama_model_mimo2::load_arch_hparams(llama_model_loader & ml) {ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa);ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa, false);- ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer());+ ml.get_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl);float value_scale = 0.0f;if (ml.get_key(LLM_KV_ATTENTION_VALUE_SCALE, value_scale, false) && value_scale != 1.0f) {