happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix GLM 4.7 Lite MoE gating func (#18980) 

* Fix GLM 4.7 MoE gating func

* Update src/models/deepseek2.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update src/llama-model.cpp

Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
This commit is contained in:
Piotr Wilkin (ilintar) 2026-01-21 12:35:20 +01:00 committed by GitHub
parent 37c35f0e1c
commit 12a4a47e6a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
src/llama-model.cpp
View File

@ -1713,7 +1713,12 @@ void llama_model::load_hparams(llama_model_loader & ml) {
if (hparams.expert_gating_func == LLAMA_EXPERT_GATING_FUNC_TYPE_NONE) {
// for compatibility with existing DeepSeek V2 and V2.5 GGUFs
// that have no expert_gating_func model parameter set
hparams.expert_gating_func = LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX;
if ((hparams.n_layer == 47 || hparams.n_layer == 48) && n_vocab == 154880) {
// GLM 4.7 Lite
hparams.expert_gating_func = LLAMA_EXPERT_GATING_FUNC_TYPE_SIGMOID;
} else {
hparams.expert_gating_func = LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX;
}
}
if (ml.get_key(LLM_KV_ROPE_SCALING_YARN_LOG_MUL, hparams.rope_yarn_log_mul, 0.0f)) {