vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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 * 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);