Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-04 02:37:27 +02:00
Code Issues Packages Projects Releases Wiki Activity

model : fix gemma4-assistant (#28183)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2026-09-01 19:58:44 +03:00
committed by GitHub
parent d11b3cc7ed
commit 73159c3039
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+1 -1
View File
@@ -1224,7 +1224,7 @@ void llama_model_base::load_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_BLOCK_COUNT, hparams.n_layer_all);
GGML_ASSERT(hparams.n_layer_all > 0 && hparams.n_layer_all <= LLAMA_MAX_LAYERS);
ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false);
GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all);
GGML_ASSERT(hparams.n_layer_nextn <= hparams.n_layer_all);
ml.get_key(LLM_KV_EXPERT_COUNT, hparams.n_expert, false);
ml.get_key(LLM_KV_EXPERT_USED_COUNT, hparams.n_expert_used, false);
ml.get_key(LLM_KV_EXPERT_GROUP_COUNT, hparams.n_expert_groups, false);
src/models/gemma4-assistant.cpp
+1 -1
View File
@@ -4,7 +4,7 @@ void llama_model_gemma4_assistant::load_arch_hparams(llama_model_loader & ml) {
hparams.n_embd_inp_impl = hparams.n_embd_out();
hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;
ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer());
ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer_all);
uint32_t n_kv_shared_layers = 0;
ml.get_key(LLM_KV_ATTENTION_SHARED_KV_LAYERS, n_kv_shared_layers, false);