llama : fix old glm4 models (#11670)

diff --git a/src/llama.cpp b/src/llama.cpp
index aae3c69b5a653233a2d9bbd3ea21f2963b8df7bb..3d5a928a8e00e525cfbacb1f576d7201c8755f06 100644 (file)
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -7217,7 +7217,7 @@ struct llm_build_context {
                 struct ggml_tensor * Qcur = nullptr;
                 struct ggml_tensor * Kcur = nullptr;
                 struct ggml_tensor * Vcur = nullptr;
-                if (model.type == LLM_TYPE_1_5B || model.type == LLM_TYPE_4B || model.type == LLM_TYPE_9B) {
+                if (model.layers[il].wqkv == nullptr) {
                     Qcur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wq, cur);
                     if (model.layers[il].bq) {
                         Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);