sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-01 22:54:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: llama arch implementation (#17665)

Browse Source
This commit is contained in:
Gilad S.
2025-12-01 22:21:13 +02:00
committed by GitHub
parent ec18edfcba
commit 00c361fe53
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-model.cpp
View File

@@ -626,6 +626,8 @@ void llama_model::load_hparams(llama_model_loader & ml) {
switch (arch) {
case LLM_ARCH_LLAMA:
{
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
if (hparams.n_expert == 8) {
switch (hparams.n_layer) {
case 32: type = LLM_TYPE_8x7B; break;