tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-01 21:15:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix old glm4 models (#11670)

Browse Source
This commit is contained in:
tv1wnd
2025-02-06 22:48:51 +01:00
committed by GitHub
parent 8a59053f63
commit 855cd0734a
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama.cpp
View File

@ -7217,7 +7217,7 @@ struct llm_build_context {
struct ggml_tensor * Qcur = nullptr; struct ggml_tensor * Qcur = nullptr;
struct ggml_tensor * Kcur = nullptr; struct ggml_tensor * Kcur = nullptr;
struct ggml_tensor * Vcur = 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); Qcur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wq, cur);
if (model.layers[il].bq) { if (model.layers[il].bq) {
Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq); Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);