Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

llama: various bug fixes (#26051)

Browse Source
This commit is contained in:
Xuan-Son Nguyen
2026-07-24 18:56:42 +02:00
committed by GitHub
parent fa72aeccb2
commit 298219f985
7 changed files with 46 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+1
View File
@@ -1083,6 +1083,7 @@ void llama_model_base::load_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_ATTENTION_CAUSAL, hparams.causal_attn, false);
ml.get_key(LLM_KV_POOLING_TYPE, hparams.pooling_type, false);
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_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);